Blog
/
/
May 12, 2021

How AI Protects Critical Infrastructure From Ransomware

Explore the role of AI in safeguarding critical infrastructure from ransomware, as revealed by Darktrace's latest insights.
No items found.
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.
No items found.
Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
12
May 2021

Modern Threats to OT Environments

At the 2021 RSA cyber security conference, US Secretary of Homeland Security Alejandro Mayorkas made an era-defining statement regarding the cyber security landscape: “Let me be clear: ransomware now poses a national security threat.”

Last weekend, Mayorkas’ words rang true. A ransomware attack on the Colonial Pipeline – responsible for nearly half of the US East Coast’s diesel, gasoline, and jet fuel – resulted in the shutdown of a critical fuel network supplying a number of Eastern states.

The fallout from the attack demonstrated how widespread and damaging the consequences of ransomware can be. Against critical infrastructure and utilities, cyber-attacks have the potential to disrupt supplies, harm the environment, and even threaten human lives.

Though full details remain to be confirmed, the attack is reported to have been conducted by an affiliate of the cyber-criminal group called DarkSide, and likely leveraged common remote desktop tools. Remote access has been enabled as an exploitable vulnerability within critical infrastructure by the shift to remote work that many organizations made last year, including those with Industrial Control Systems (ICS) and Operational Technology (OT).

The rise of industrial ransomware

Ransomware against industrial environments is on the rise, with a reported 500% increase since 2018. Oftentimes, these threats leverage the convergence of IT and OT systems, first targeting IT before pivoting to OT. This was seen with the EKANS ransomware that included ICS processes in its ‘kill list’, as well as the Cring ransomware that compromised ICS after first exploiting a vulnerability in a virtual private network (VPN).

It remains to be seen whether the initial attack vector in the Colonial Pipeline compromise exploited a technical vulnerability, compromised credentials, or a targeted spear phishing campaign. It has been reported that the attack first impacted IT systems, and that Colonial then shut down OT operations as a safety precaution. Colonial confirms that the ransomware “temporarily halted all pipeline operations and affected some of our IT systems,” showing that, ultimately, both OT and IT were affected. This is a great example of how many OT systems depend on IT, such that an IT cyber-attack has the ability to take down OT and ICS processes.

In addition to locking down systems, the threat actors also stole 100GB of sensitive data from Colonial. This kind of double extortion attack — in which data is exfiltrated before files are encrypted — has unfortunately become the norm rather than the exception, with over 70% of ransomware attacks involving exfiltration. Some ransomware gangs have even announced that they are dropping encryption altogether in favor of data theft and extortion methods.

Earlier this year, Darktrace defended against a double extortion ransomware attack waged against a critical infrastructure organization, which also leveraged common remote access tools. This blog will outline the threat find in depth, showing how Darktrace’s self-learning AI responded autonomously to an attack strikingly similar to the Colonial Pipeline incident.

Darktrace threat find

Ransomware against electric utilities equipment supplier

In an attack against a North American equipment supplier for electrical utilities earlier this year, Darktrace/OT demonstrated its ability to protect critical infrastructure against double extortion ransomware that targeted organizations with ICS and OT.

The ransomware attack initially targeted IT systems, and, thanks to self-learning Cyber AI, was stopped before it could spill over into OT and disrupt operations.

The attacker first compromised an internal server in order to exfiltrate data and deploy ransomware over the course of 12 hours. The short amount of time between initial compromise and deployment is unusual, as ransomware threat actors often wait several days to spread stealthily as far across the cyber ecosystem as possible before striking.

Figure 1: A timeline of the attack

How did the attack bypass the rest of the security stack?

The attacker leveraged ‘Living off the Land’ techniques to blend into the business’ normal ‘patterns of life’, using a compromised admin credential and a remote management tool approved by the organization, in its attempts to remain undetected.

Darktrace commonly sees the abuse of legitimate remote management software in attackers’ arsenal of techniques, tactics, and procedures (TTPs). Remote access is also becoming an increasingly common vector of attack in ICS attacks in particular. For example, in the cyber-incident at the Florida water treatment facility last February, attackers exploited a remote management tool in attempts to manipulate the treatment process.

The specific strain of ransomware deployed by this attacker also successfully evaded detection by anti-virus by using a unique file extension when encrypting files. These forms of ‘signatureless’ ransomware easily slip past legacy approaches to security that rely on rules, signatures, threat feeds, and lists of documented Common Vulnerabilities and Exposures (CVEs), as these are methods that can only detect previously documented threats.

The only way to detect never-before-seen threats like signatureless ransomware is for a technology to find anomalous behavior, rather than rely on lists of ‘known bads’. This can be achieved with self-learning technology, which spots even the most subtle deviations from the normal ‘patterns of life’ for all devices, users, and all the connections between them.

Darktrace insights

Initial compromise and establishing foothold

Despite the abuse of a legitimate tool and the absence of known signatures, Darktrace/OT was able to use a holistic understanding of normal activity to detect the malicious activity at multiple points in the attack lifecycle.

The first clear sign of an emerging threat that was alerted by Darktrace was the unusual use of a privileged credential. The device also served an unusual remote desktop protocol (RDP) connection from a Veeam server shortly before the incident, indicating that the attacker may have moved laterally from elsewhere in the network.

Three minutes later, the device initiated a remote management session which lasted 21 hours. This allowed the attacker to move throughout the broader cyber ecosystem while remaining undetected by traditional defences. Darktrace, however, was able to detect unusual remote management usage as another early warning indicative of an attack.

Double threat part one: Data exfiltration

One hour after the initial compromise, Darktrace detected unusual volumes of data being sent to a 100% rare cloud storage solution, pCloud. The outbound data was encrypted using SSL, but Darktrace created multiple alerts relating to large internal downloads and external uploads that were a significant deviation from the device’s normal ‘pattern of life’.

The device continued to exfiltrate data for nine hours. Analysis of the files downloaded by the device, which were transferred using the unencrypted SMB protocol, suggests that they were sensitive in nature. Fortunately, Darktrace was able to pinpoint the specific files that were exfiltrated so that the customer could immediately evaluate the potential implications of the compromise.

Double threat part two: File encryption

A short time later, at 01:49 local time, the compromised device began encrypting files in a SharePoint back-up share drive. Over the next three and a half hours, the device encrypted over 13,000 files on at least 20 SMB shares. In total, Darktrace produced 23 alerts for the device in question, which amounted to 48% of all the alerts produced in the corresponding 24-hour period.

Darktrace’s Cyber AI Analyst then automatically launched an investigation, identifying the internal data transfers and the file encryption over SMB. From this, it was able to present incident reports that connected the dots among these disparate anomalies, piecing them together into a coherent security narrative. This put the security team in a position to immediately take remediating action.

If the customer had been using Darktrace’s autonomous response technology, there is no doubt the activity would have been halted before significant volumes of data could have been exfiltrated or files encrypted. Fortunately, after seeing both the alerts and Cyber AI Analyst reports, the customer was able to use Darktrace’s ‘Ask the Expert’ (ATE) service for incident response to mitigate the impact of the attack and assist with disaster recovery.

Figure 2: AI Analyst Incident reporting an unusual reprogram command using the MODBUS protocol. The incident includes a plain English summary, relevant technical information, and the investigation process used by the AI.  

Detecting the threat before it could disrupt critical infrastructure

The targeted supplier was overseeing OT and had close ties to critical infrastructure. By facilitating the early-stage response, Darktrace prevented the ransomware from spreading further onto the factory floor. Crucially, Darktrace also minimized operational disruption, helping to avoid the domino effect which the attack could have had, affecting not only the supplier itself, but also the electric utilities that this supplier supports.

As both the recent Colonial Pipeline incident and the above threat find reveal, ransomware is a pressing concern for organizations overseeing industrial operations across all forms of critical infrastructure, from pipelines to the power grid and its suppliers. With self-learning AI, these attack vectors can be dealt with before the damage is done through real-time threat detection, autonomous investigations, and — if activated — targeted machine-speed response.

Looking forward: Using Self-Learning AI to protect critical infrastructure across the board

In late April, the Biden administration announced an ambitious effort to “safeguard US critical infrastructure from persistent and sophisticated threats.” The Department of Energy’s (DOE) 100-day plan specifically seeks technologies “that will provide cyber visibility, detection, and response capabilities for industrial control systems of electric utilities.”

The Biden administration’s cyber sprint clearly calls for a technology that protects critical energy infrastructure, rather than merely best practice measures and regulations. As seen in the above threat find, Darktrace AI is a powerful technology that leverages unsupervised machine learning to autonomously safeguard critical infrastructure and its suppliers with machine speed and precision.

Darktrace enhances detection, mitigation, and forensic capabilities to detect  sophisticated and novel attacks, along with insider threats and pre-existing infections, using Self-Learning Cyber AI, without rules, signatures, or lists of CVEs. Incident investigations provided in real time by Cyber AI Analyst jumpstart remediation with actionable insights, containing emerging attacks at their early stages, before they escalate into crisis.

Enable near real-time situational awareness and response capabilities

Darktrace immediately understands, identifies, and investigates all anomalous activity in ICS/OT networks, whether human or machine driven. Additionally, Darktrace actions targeted response where appropriate to neutralize threats, either actively or in human confirmation mode. Because Self-learning AI adapts alongside evolutions in the ecosystem, organizations benefit from real-time awareness with no tuning or human input necessary

Deploy technologies to increase visibility of threats in ICS and OT systems

Darktrace contextualizes security events, adapts to novel techniques, and translates findings into a security narrative that can be actioned by humans in minutes. Delivering a unified view across IT and OT systems.

Darktrace detects, investigates, and responds to threats at higher Purdue levels and in IT systems before they ‘spill over’ into OT. ‘Plug and play’ deployment seamlessly integrates with technological architecture, presenting 3D network topology with granular visibility into all users, devices, and subnets.

Darktrace's asset identification continuously catalogues all ICS/OT devices and identifies and investigates all threatening activity indicative of emerging attacks – be it ICS ransomware, APTs, zero-day exploits, insider threats, pre-existing infections, DDoS, crypto-mining, misconfigurations, or never-before-seen attacks.

Thanks to Darktrace analyst Oakley Cox for his insights on the above threat find.

Darktrace model detections:

  • Initial compromise:
  • User / New Admin Credential on Client
  • Data exfiltration:
  • Anomalous Connection / Uncommon 1 GiB Outbound
  • Anomalous Connection / Low and Slow Exfiltration
  • Device / Anomalous SMB Followed by Multiple Model Breaches
  • Anomalous Connection / Download and Upload
  • File encryption:
  • Compromise / Ransomware / Suspicious SMB Activity
  • Anomalous Connection / SMB Enumeration
  • Device / Anomalous RDP Followed by Multiple Model Breaches
  • Anomalous File / Internal / Additional Extension Appended to SMB File
  • Anomalous Connection / Sustained MIME Type Conversion
  • Anomalous Connection / Suspicious Read Write Ratio
  • Device / Multiple Lateral Movement Model Breaches

No items found.
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.
No items found.

More in this series

No items found.

Blog

/

/

July 16, 2025

Introducing the AI Maturity Model for Cybersecurity

Default blog imageDefault blog image

AI adoption in cybersecurity: Beyond the hype

Security operations today face a paradox. On one hand, artificial intelligence (AI) promises sweeping transformation from automating routine tasks to augmenting threat detection and response. On the other hand, security leaders are under immense pressure to separate meaningful innovation from vendor hype.

To help CISOs and security teams navigate this landscape, we’ve developed the most in-depth and actionable AI Maturity Model in the industry. Built in collaboration with AI and cybersecurity experts, this framework provides a structured path to understanding, measuring, and advancing AI adoption across the security lifecycle.

Overview of AI maturity levels in cybersecurity

Why a maturity model? And why now?

In our conversations and research with security leaders, a recurring theme has emerged:

There’s no shortage of AI solutions, but there is a shortage of clarity and understanding of AI uses cases.

In fact, Gartner estimates that “by 2027, over 40% of Agentic AI projects will be canceled due to escalating costs, unclear business value, or inadequate risk controls. Teams are experimenting, but many aren’t seeing meaningful outcomes. The need for a standardized way to evaluate progress and make informed investments has never been greater.

That’s why we created the AI Security Maturity Model, a strategic framework that:

  • Defines five clear levels of AI maturity, from manual processes (L0) to full AI Delegation (L4)
  • Delineating the outcomes derived between Agentic GenAI and Specialized AI Agent Systems
  • Applies across core functions such as risk management, threat detection, alert triage, and incident response
  • Links AI maturity to real-world outcomes like reduced risk, improved efficiency, and scalable operations

[related-resource]

How is maturity assessed in this model?

The AI Maturity Model for Cybersecurity is grounded in operational insights from nearly 10,000 global deployments of Darktrace's Self-Learning AI and Cyber AI Analyst. Rather than relying on abstract theory or vendor benchmarks, the model reflects what security teams are actually doing, where AI is being adopted, how it's being used, and what outcomes it’s delivering.

This real-world foundation allows the model to offer a practical, experience-based view of AI maturity. It helps teams assess their current state and identify realistic next steps based on how organizations like theirs are evolving.

Why Darktrace?

AI has been central to Darktrace’s mission since its inception in 2013, not just as a feature, but the foundation. With over a decade of experience building and deploying AI in real-world security environments, we’ve learned where it works, where it doesn’t, and how to get the most value from it. This model reflects that insight, helping security leaders find the right path forward for their people, processes, and tools

Security teams today are asking big, important questions:

  • What should we actually use AI for?
  • How are other teams using it — and what’s working?
  • What are vendors offering, and what’s just hype?
  • Will AI ever replace people in the SOC?

These questions are valid, and they’re not always easy to answer. That’s why we created this model: to help security leaders move past buzzwords and build a clear, realistic plan for applying AI across the SOC.

The structure: From experimentation to autonomy

The model outlines five levels of maturity :

L0 – Manual Operations: Processes are mostly manual with limited automation of some tasks.

L1 – Automation Rules: Manually maintained or externally-sourced automation rules and logic are used wherever possible.

L2 – AI Assistance: AI assists research but is not trusted to make good decisions. This includes GenAI agents requiring manual oversight for errors.

L3 – AI Collaboration: Specialized cybersecurity AI agent systems  with business technology context are trusted with specific tasks and decisions. GenAI has limited uses where errors are acceptable.

L4 – AI Delegation: Specialized AI agent systems with far wider business operations and impact context perform most cybersecurity tasks and decisions independently, with only high-level oversight needed.

Each level reflects a shift, not only in technology, but in people and processes. As AI matures, analysts evolve from executors to strategic overseers.

Strategic benefits for security leaders

The maturity model isn’t just about technology adoption it’s about aligning AI investments with measurable operational outcomes. Here’s what it enables:

SOC fatigue is real, and AI can help

Most teams still struggle with alert volume, investigation delays, and reactive processes. AI adoption is inconsistent and often siloed. When integrated well, AI can make a meaningful difference in making security teams more effective

GenAI is error prone, requiring strong human oversight

While there is a lot of hype around GenAI agentic systems, teams will need to account for inaccuracy and hallucination in Agentic GenAI systems.

AI’s real value lies in progression

The biggest gains don’t come from isolated use cases, but from integrating AI across the lifecycle, from preparation through detection to containment and recovery.

Trust and oversight are key initially but evolves in later levels

Early-stage adoption keeps humans fully in control. By L3 and L4, AI systems act independently within defined bounds, freeing humans for strategic oversight.

People’s roles shift meaningfully

As AI matures, analyst roles consolidate and elevate from labor intensive task execution to high-value decision-making, focusing on critical, high business impact activities, improving processes and AI governance.

Outcome, not hype, defines maturity

AI maturity isn’t about tech presence, it’s about measurable impact on risk reduction, response time, and operational resilience.

[related-resource]

Outcomes across the AI Security Maturity Model

The Security Organization experiences an evolution of cybersecurity outcomes as teams progress from manual operations to AI delegation. Each level represents a step-change in efficiency, accuracy, and strategic value.

L0 – Manual Operations

At this stage, analysts manually handle triage, investigation, patching, and reporting manually using basic, non-automated tools. The result is reactive, labor-intensive operations where most alerts go uninvestigated and risk management remains inconsistent.

L1 – Automation Rules

At this stage, analysts manage rule-based automation tools like SOAR and XDR, which offer some efficiency gains but still require constant tuning. Operations remain constrained by human bandwidth and predefined workflows.

L2 – AI Assistance

At this stage, AI assists with research, summarization, and triage, reducing analyst workload but requiring close oversight due to potential errors. Detection improves, but trust in autonomous decision-making remains limited.

L3 – AI Collaboration

At this stage, AI performs full investigations and recommends actions, while analysts focus on high-risk decisions and refining detection strategies. Purpose-built agentic AI systems with business context are trusted with specific tasks, improving precision and prioritization.

L4 – AI Delegation

At this stage, Specialized AI Agent Systems performs most security tasks independently at machine speed, while human teams provide high-level strategic oversight. This means the highest time and effort commitment activities by the human security team is focused on proactive activities while AI handles routine cybersecurity tasks

Specialized AI Agent Systems operate with deep business context including impact context to drive fast, effective decisions.

Join the webinar

Get a look at the minds shaping this model by joining our upcoming webinar using this link. We’ll walk through real use cases, share lessons learned from the field, and show how security teams are navigating the path to operational AI safely, strategically, and successfully.

Continue reading
About the author

Blog

/

/

July 16, 2025

Forensics or Fauxrensics: Five Core Capabilities for Cloud Forensics and Incident Response

Default blog imageDefault blog image

The speed and scale at which new cloud resources can be spun up has resulted in uncontrolled deployments, misconfigurations, and security risks. It has had security teams racing to secure their business’ rapid migration from traditional on-premises environments to the cloud.

While many organizations have successfully extended their prevention and detection capabilities to the cloud, they are now experiencing another major gap: forensics and incident response.

Once something bad has been identified, understanding its true scope and impact is nearly impossible at times. The proliferation of cloud resources across a multitude of cloud providers, and the addition of container and serverless capabilities all add to the complexities. It’s clear that organizations need a better way to manage cloud incident response.

Security teams are looking to move past their homegrown solutions and open-source tools to incorporate real cloud forensics capabilities. However, with the increased buzz around cloud forensics, it can be challenging to decipher what is real cloud forensics, and what is “fauxrensics.”

This blog covers the five core capabilities that security teams should consider when evaluating a cloud forensics and incident response solution.

[related-resource]

1. Depth of data

There have been many conversations among the security community about whether cloud forensics is just log analysis. The reality, however, is that cloud forensics necessitates access to a robust dataset that extends far beyond traditional log data sources.

While logs provide valuable insights, a forensics investigation demands a deeper understanding derived from multiple data sources, including disk, network, and memory, within the cloud infrastructure. Full disk analysis complements log analysis, offering crucial context for identifying the root cause and scope of an incident.

For instance, when investigating an incident involving a Kubernetes cluster running on an EC2 instance, access to bash history can provide insights into the commands executed by attackers on the affected instance, which would not be available through cloud logs alone.

Having all of the evidence in one place is also a capability that can significantly streamline investigations, unifying your evidence be it disk images, memory captures or cloud logs, into a single timeline allowing security teams to reconstruct an attacks origin, path and impact far more easily. Multi–cloud environments also require platforms that can support aggregating data from many providers and services into one place. Doing this enables more holistic investigations and reduces security blind spots.

There is also the importance of collecting data from ephemeral resources in modern cloud and containerized environments. Critical evidence can be lost in seconds as resources are constantly spinning up and down, so having the ability to capture this data before its gone can be a huge advantage to security teams, rather than having to figure out what happened after the affected service is long gone.

darktrace / cloud, cado, cloud logs, ost, and memory information. value of cloud combined analysis

2. Chain of custody

Chain of custody is extremely critical in the context of legal proceedings and is an essential component of forensics and incident response. However, chain of custody in the cloud can be extremely complex with the number of people who have access and the rise of multi-cloud environments.

In the cloud, maintaining a reliable chain of custody becomes even more complex than it already is, due to having to account for multiple access points, service providers and third parties. Having automated evidence tracking is a must. It means that all actions are logged, from collection to storage to access. Automation also minimizes the chance of human error, reducing the risk of mistakes or gaps in evidence handling, especially in high pressure fast moving investigations.

The ability to preserve unaltered copies of forensic evidence in a secure manner is required to ensure integrity throughout an investigation. It is not just a technical concern, its a legal one, ensuring that your evidence handling is documented and time stamped allows it to stand up to court or regulatory review.

Real cloud forensics platforms should autonomously handle chain of custody in the background, recording and safeguarding evidence without human intervention.

3. Automated collection and isolation

When malicious activity is detected, the speed at which security teams can determine root cause and scope is essential to reducing Mean Time to Response (MTTR).

Automated forensic data collection and system isolation ensures that evidence is collected and compromised resources are isolated at the first sign of malicious activity. This can often be before an attacker has had the change to move latterly or cover their tracks. This enables security teams to prevent potential damage and spread while a deeper-dive forensics investigation takes place. This method also ensures critical incident evidence residing in ephemeral environments is preserved in the event it is needed for an investigation. This evidence may only exist for minutes, leaving no time for a human analyst to capture it.

Cloud forensics and incident response platforms should offer the ability to natively integrate with incident detection and alerting systems and/or built-in product automation rules to trigger evidence capture and resource isolation.

4. Ease of use

Security teams shouldn’t require deep cloud or incident response knowledge to perform forensic investigations of cloud resources. They already have enough on their plates.

While traditional forensics tools and approaches have made investigation and response extremely tedious and complex, modern forensics platforms prioritize usability at their core, and leverage automation to drastically simplify the end-to-end incident response process, even when an incident spans multiple Cloud Service Providers (CSPs).

Useability is a core requirement for any modern forensics platform. Security teams should not need to have indepth knowledge of every system and resource in a given estate. Workflows, automation and guidance should make it possible for an analyst to investigate whatever resource they need to.

Unifying the workflow across multiple clouds can also save security teams a huge amount of time and resources. Investigations can often span multiple CSP’s. A good security platform should provide a single place to search, correlate and analyze evidence across all environments.

Offering features such as cross cloud support, data enrichment, a single timeline view, saved search, and faceted search can help advanced analysts achieve greater efficiency, and novice analysts are able to participate in more complex investigations.

5. Incident preparedness

Incident response shouldn't just be reactive. Modern security teams need to regularly test their ability to acquire new evidence, triage assets and respond to threats across both new and existing resources, ensuring readiness even in the rapidly changing environments of the cloud.  Having the ability to continuously assess your incident response and forensics workflows enables you to rapidly improve your processes and identify and mitigate any gaps identified that could prevent the organization from being able to effectively respond to potential threats.

Real forensics platforms deliver features that enable security teams to prepare extensively and understand their shortcomings before they are in the heat of an incident. For example, cloud forensics platforms can provide the ability to:

  • Run readiness checks and see readiness trends over time
  • Identify and mitigate issues that could prevent rapid investigation and response
  • Ensure the correct logging, management agents, and other cloud-native tools are appropriately configured and operational
  • Ensure that data gathered during an investigation can be decrypted
  • Verify that permissions are aligned with best practices and are capable of supporting incident response efforts

Cloud forensics with Darktrace

Darktrace delivers a proactive approach to cyber resilience in a single cybersecurity platform, including cloud coverage. Darktrace / CLOUD is a real time Cloud Detection and Response (CDR) solution built with advanced AI to make cloud security accessible to all security teams and SOCs. By using multiple machine learning techniques, Darktrace brings unprecedented visibility, threat detection, investigation, and incident response to hybrid and multi-cloud environments.

Darktrace’s cloud offerings have been bolstered with the acquisition of Cado Security Ltd., which enables security teams to gain immediate access to forensic-level data in multi-cloud, container, serverless, SaaS, and on-premises environments.

[related-resource]

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