Blog
/
/
March 20, 2019

The Invisible Threat: How AI Catches the Ursnif Trojan

The cyber AI approach successfully detected the Ursnif infections even though the new variant of this malware was unknown to security vendors at the time.
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
Max Heinemeyer
Global Field CISO
Default blog image
20
Mar 2019

Over the past few months, I’ve analyzed some of the world’s stealthiest trojan attacks like Emotet, which employ deception to bypass traditional security tools that rely on rules and signatures. Guest contributor Keith Siepel also explained how cyber AI defenses managed to catch a zero-day trojan on his firm’s network for which no such rules or signatures yet exist. Indeed, with the incidence of banking trojans having increased by 239% among our customer base last year, it appears that this kind of subterfuge is the new normal.

However, one particularly sophisticated trojan, Ursnif, takes deception a step further evidence of which we are still seeing emerge. Rather than writing executable files that contain malicious code, some of its variants instead exploit vulnerabilities inherent to a user’s own applications, essentially turning the victim’s computer against them. The result of this increasingly common technique is that — once the victim has been tricked into clicking a malicious link or duped into opening an attachment via a phishing email — Ursnif begins to ‘live off the land’, blending into the victim’s environment. And by exploiting Microsoft Office and Windows features, such as document macros, PsExec, and PowerShell scripts, Ursnif can execute commands directly from the computer’s RAM.

One of the most prevalent and destructive strains of the Gozi banking malware, Ursnif was recently placed at the center of a new campaign that saw it dramatically expand its functionality. Originally created to infect hosts with spyware in order to steal sensitive banking information and user credentials, it can now also deploy advanced ransomware like GandCrab. These new functions are aided by the elusive trojan’s aforementioned file-less capabilities, which render it invisible to many security tools and allow it to hide in plain sight within legitimate, albeit corrupted applications. Shining a light on Ursnif therefore requires AI tools that can learn to spot when these applications act abnormally:

Cyber AI detects Ursnif on multiple client networks

First campaign: February 4, 2019

Darktrace detected the initial Ursnif compromise on a customer’s network when it caught several devices connecting to a highly unusual endpoint and subsequently downloading masqueraded files, causing Darktrace’s “Anomalous File / Masqueraded File Transfer” model to breach. Such files are often masqueraded as other file types not only to bypass traditional security measures but also to deceive users — for instance, with the intention of tricking a user into executing a file received in a malicious email by disguising it as a document.

As it happens, this Ursnif variant was a zero-day at the time Darktrace detected it, meaning that its files were unknown to antivirus vendors. But while the never-before-seen files bypassed the customer’s endpoint tools, Darktrace AI leveraged its understanding of the unique ‘pattern of life’ for every user and device in the customer’s network to flag these file downloads as threatening anomalies — without relying on signatures.

A sample of the masqueraded files initially downloaded:

File: xtex13.gas
File MIME type: application/x-dosexec
Size: 549.38 KB
Connection UID: C8SlueG1mT7VdcJ00

File: zyteb17.gas
File MIME type: application/x-dosexec
SHA-1 hash: 4ed60393575d6b47bd82eeb03629bdcb8876a73f
Size: 276.48 KB

File: File: adnaz2.gas
File MIME type: application/x-dosexec
Size: 380.93 KB
Connection UID: CmPOzP1AC4tzuuuW00

A sample of the endpoints detected:

kieacsangelita[.]city · 209.141.60[.]214
muikarellep[.]band · 46.29.167[.]73
cjasminedison[.]com · 185.120.58[.]13

Following the initial suspicious downloads, the compromised devices were further observed making regular connections to multiple rare destinations not previously seen on the affected network in a pattern of beaconing connectivity. In some cases, Darktrace marked these external destinations as suspicious when it recognized the hostnames they queried as algorithm-generated domains. High volumes of DNS requests for such domains is a common characteristic of malware infections, which use this tactic to maintain communication with C2 servers in spite of domain black-listing. In other cases, the endpoints were deemed suspicious because of their use of self-signed SSL certificates, which cyber-criminals often use because they do not require verification by a trusted authority.

In fact, the large volume of anomalous connections commonly triggered a number of Darktrace’s behavioral models, including:

Compromise / DGA Beacon
Anomalous Connection / Suspicious Self-Signed SSL
Compromise / High Volume of Connections with Beacon Score
Compromise / Beaconing Activity To Rare External Endpoint

Beaconing is a method of communication frequently seen when a compromised device attempts to relay information to its control infrastructure in order to receive further instructions. This behavior is characterized by persistent external connections to one or multiple endpoints, a pattern that was repeatedly observed for those devices that had previously downloaded malicious files from the endpoints later associated with the Ursnif campaign. While beaconing behavior to unusual destinations is not necessarily always indicative of infection, Darktrace AI concluded that, in combination with the suspicious file downloads, this type of activity represented a clear indication of compromise.

Figure 1: A device event log that shows the device had connected to internal mail servers shortly before downloading the malicious files.

Lateral movement and file-less capabilities

In the wake of the initial compromise, Darktrace AI also detected Ursnif’s lateral movement and file-less capabilities in real time. In the case of one infected device, an “Anomalous Connection / High Volume of New Service Control” model breach was triggered following the aforementioned suspicious activities. The device in question was flagged after making anomalous SMB connections to at least 47 other internal devices, and after accessing file shares which it had not previously connected. Subsequently, the device was observed writing to the other devices’ service control pipe – a channel used for the remote control of services. The anomalous use of these remote-control channels represent compelling examples of how Ursnif leverages its file-less capabilities to facilitate lateral movement.

Figure 2: Volume of SMB writes made to the service control pipe on internal devices by one of the infected devices, as shown on the Darktrace UI.

Although network administrators often use remote control channels for legitimate purposes, Darktrace AI considered this particular usage highly suspicious, particularly as both devices had previously breached a number of behavioral models as a result of infection.

Second campaign: March 18, 2019

A second Ursnif campaign was detected just this week. At the time of detection, no OSINT was available for the C2 servers nor the malware samples.

On a US manufacturer’s network, the initial malware download took place from: xqzuua1594[.]com/loq91/10x.php?l=mow1.jad hosted on IP 94.154.10[.]62.
Every single malware download is unique. This is indicating auto-patching or a malware factory working in the background.
Darktrace immediately identified this as another Anomalous File / Masqueraded File Transfer.

Directly after this, initial C2 was observed with the following parameters:

HTTP GET to: vwdlpknpsierra[.]email
Destination IP: 162.248.225[.]14
URI: /images/CKicJCsNNNfaJwX6CJ/0Ohp3OUfj/pI_2FszUK7ybqh33Qdwz/bOUeatCG2Qfks5DTzzO/H6SeiL8YozEYXKfornjfVt/hBgfcPVPCOf1H/2qo12IGl/L3B18ld4ZSx37TbdTUpALih/A5dl8FVHel/jMPIKnQfd/H.avi
User Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko

What’s interesting here is that the C2 server provides a Sufee Admin login page:

This C2 appears to have bad operational security (OPSEC) as browsing random URIs on the server reveals some of the dashboard’s contents:

The initial C2 communication was followed by sustained TCP beaconing to ksylviauudaren[.]band on 185.180.198[.]245 over port 443 with SSL encryption using a self-signed certificate. Darktrace highlighted this C2 behavior as Compromise / Sustained TCP Beaconing Activity To Rare Endpoint and Anomalous Connection / Repeated Rare External SSL Self-Signed IP.

As of the writing of this article, the domain ksylviauudaren[.]band was still not recognized in OSINT as malicious – highlighting again Darktrace’s independence of signatures and rules to catch previously unknown threats.

Conclusion

The cyber AI approach successfully detected the Ursnif infections even though the new variant of this malware was unknown to security vendors at the time. Moreover, it even managed to catch Ursnif’s file-less capabilities for lateral movement through its modelling of expected patterns of connectivity. In terms of the wider security context, the ease with which cyber AI flagged such sophisticated malware — malware which takes action by corrupting a computer’s own applications — further demonstrates that AI anomaly detection is the only way to navigate a threat landscape increasingly populated by near-invisible trojans.

IoCs

kieacsangelita[.]city · 209.141.60[.]214
muikarellep[.]band · 46.29.167[.]73
cjasminedison[.]com · 185.120.58[.]13
xqzuua1594[.]com · 94.154.10.[6]2
vwdlpknpsierra[.]email · 162.248.225[.]14
ksylviauudaren[.]band · 185.180.198[.]245

‍

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
Max Heinemeyer
Global Field CISO

More in this series

No items found.

Blog

/

AI

/

November 18, 2026

Agentic attacks in the wild: Inside three ARTEX investigations

Default blog imageDefault blog image

Key insights

·       Darktrace observed activity in several customer environments involving infrastructure and behaviors associated with reported ARTEX-enabled campaigns, including activity linked to China-nexus espionage and financially motivated attacks.

·       In the higher-confidence cases, known infrastructure appeared alongside beaconing, unusual TLS, reconnaissance, tunneling, script retrieval, SMB activity and external data transfer. One Azure case had no observed network command and control at all, only key listing and application identity activity.

·       ARTEX is now used by actors with different objectives. Identifying the framework can help locate relevant activity, while the behavior around the affected system provides the stronger evidence for understanding compromise and attribution.

‍

Introduction

Attackers have moved beyond using AI for phishing and are running agentic frameworks; open-source tools like ARTEX, CAIRN, PentAGI and Hexstrike that let AI agents scan, exploit and move through an environment with little human input [1]. ARTEX has moved quickly from an offensive security project into live intrusion activity. Since at least August 2026, the framework has been associated with espionage, financially motivated attacks and opportunistic campaigns across government, financial services, technology, defense, telecommunications and other sectors. The FBI has documented ARTEX activity spanning reconnaissance, exploitation, credential abuse, lateral movement, collection, command and control, and exfiltration [2].

Darktrace has observed activity in customer environments that overlaps with infrastructure, tooling and behaviors reported in several of these campaigns. The cases below highlight how those intrusions appeared on the network, including the activity visible before an analyst can determine which actor or framework may be responsible.

ARTEX as part of the attacker workflow

ARTEX is an open-source, multi-agent offensive security platform that converts high-level objectives into actions carried out by specialized agents [2]. Operators have used it to automate activity across the attack lifecycle, including scanning, exploitation, credential activity and post-compromise operations. Some reported intrusions moved from initial targeting to privileged access in under three hours [2].

The framework is now associated with actors pursuing different objectives and using different post-exploitation tooling. The original public repository was removed in October 2026, but archived copies and localized versions remain available. For defenders, ARTEX is more useful as context for an investigation than as an attribution shortcut.

Darktrace observations show the same point at network level. Infrastructure linked to reported ARTEX campaigns appeared alongside beaconing, tunneling, unusual TLS, reconnaissance, file retrieval and lateral activity.

Case 1: Espionage-linked activity

Darktrace observed activity associated with BLOODALCHEMY command-and-control (C2) infrastructure in two customer environments. In one environment, five devices communicated with nginxmysql[.]com and 45.153.126[.]223 between October 23 and November 2. Both indicators had previously been linked to China-nexus espionage activity involving ARTEX [4].

The connections were accompanied by suspicious beaconing, repeated successful connections and unusual self-signed TLS. One system began making suspicious TLS connections to nginxmysql[.]com on October 23. Beaconing followed on October 24, and SMB scanning appeared later in the sequence. Other affected systems subsequently communicated with previously unseen external endpoints.

Prior to the observed C2, Darktrace detected curl requests retrieving executable and script content including /systemd, /wazuh, linux_amd64, u.sh and q.sh. Related telemetry included DRSGetNCChanges activity consistent with DCSync, LDAP enumeration, DNS zone transfers, network scanning, certificate downloads and SMB writes involving start.bat.

‍

Figure 1: Darktrace investigation showing suspicious network activity associated with infrastructure linked to reported ARTEX activity.

‍

Figure 2: Darktrace detection showing anomalous self-signed TLS activity during the espionage-linked investigation.

‍

BLOODALCHEMY has been reported in more than one China-nexus cluster [5]. SoftEther infrastructure observed in one environment provided another point of correlation with reported VAPOR PANDA tradecraft. The moderate-confidence assessment tying this to a Chinese nexus threat actor is based on infrastructure, victim context, tradecraft behavior that followed the initial connection, and public reporting.

Case 2: Financial-sector activity

In early November, Darktrace observed activity in two financial-sector environments that overlap with reported ARTEX infrastructure. On November 5, a server connected to 213.111.150[.]145:8099 and downloaded wisp-agent, associated with WISP C2 activity.

In a second environment, a device attempted connections to 85.11.167[.]52 on November 1 and 2. The connections occurred alongside beaconing to new and rare destinations, anomalous TLS, possible tunneling and unusual package downloads.

The device also communicated with temp[.]sh, ssh.localhost[.]run, localhost[.]run, termbin[.]com, pastebin[.]com and GitHub-hosted release infrastructure. The sequence showed potential tooling retrieval, C2, tunneling and use of external services capable of staging or moving data.

Figure 3: Darktrace investigation showing connections to new and rare external destinations during the financial-sector activity.

‍

Case 3: Credential collection in Azure

On October 20, Darktrace observed a sweep of credential collection in a customer’s Azure environment that is consistent with ARTEX use. The intrusion began with connections to the virtual network from 43.98.196[.]73 (Alibaba Cloud). Open-source scanning data associates the address with ARTEX.

A compromised user identity made requests to the Azure Resource Manager API, though how it was compromised is unknown. The requests listed keys and secrets across API Management, web and function apps, Cognitive Services, Event Hubs, storage accounts and a managed Kubernetes cluster. With those credentials the attacker compromised multiple application identities. The attacker then used the application identities and the user identity to retrieve more credentials, change firewall and security rules and run scripts on virtual machines. Microsoft Defender alerts showed attempted execution of scripts related to Mimikatz and Impacket.

In a cloud environment, such privileged and enumerative operations are potentially indistinguishable from legitimate administrative actions. Consequently, the sequence and context of such operations signified more than any specific API call. There was no C2 traffic to match, and listing keys and using application identities are also what administrators and automation do. A compromised user, credential retrieval across several Azure services, new application identities, more credential collection and changes to security controls only made sense together, and by then access was spreading through the cloud environment.

‍

Figure 4: Darktrace Advanced Search showing Azure AD operation names associated with the activity.

‍

Figure 5: Darktrace Advanced Search showing the Azure Resource Manager action used to execute scripts.
Figure 6: Darktrace Device Event log window showing the triggered models related to the suspicious Azure activity.

‍

Shared tooling weakens attribution signals

The three cases looked different on the network: BLOODALCHEMY infrastructure and espionage-consistent tradecraft, WISP infrastructure in financial-sector systems, and Azure identity and control-plane activity with no C2 at all.

Shared tooling has complicated attribution for years, and ARTEX adds to it because the framework carries out more of the attack, so reconnaissance, exploitation attempts and some post-compromise activity can look the same whoever set the objective. Attribution still needs infrastructure, malware, victimology, timing and the sequence of behavior inside the environment, and an ARTEX link is one input to that. Moreover, the behavior and the agent will still be shaped by the biases, preferences, and tradecraft of its operators.

At its core, ARTEX’s planner and worker agents identify and record facts, while exploring intents. However, the way the Large Language Model (LLM) chooses its next steps toward an objective is shaped fundamentally by the skills and tools available in its context. This includes its starting context, as well as various possible Model Context Protocol (MCP) plugins and user-injected context (e.g. user input mid-operation). Operators still have preferred tradecraft, and this preference shapes the pathways the harness will provide to the LLM in context prompts. Even on the same platform, customization based on operator preferences and goals will remain a key facet of campaign and actor identification.

Detection and response

Across the Darktrace cases, the stronger signals came from behavior after the connection: beaconing, abnormal TLS, reconnaissance, unusual authentication, tunneling, script retrieval, SMB activity and outbound transfer. Automated activity also produced compressed bursts of requests, sequential enumeration and repeated attempts with small changes.

With agentic tools reaching privileged access in under three hours, analysts may have only a short window to connect scanning or authentication activity to credential changes, new administrative access, tooling retrieval or lateral movement. Keeping network, identity and cloud telemetry together shows what happened before and after the first match, and whether a connection was noise or an intrusion moving toward privileged access.

ARTEX won’t be the last of these frameworks. The next ones will come with new capabilities and defaults, but an intrusion still must interact with the target environment, and that shows up in how systems, identities and applications behave even after the indicator has aged out. The harder intrusions to catch will have no infrastructure to match, just ordinary API calls and legitimate identities. Detecting those depends on knowing what normal looks like for each identity and device.

‍

Credit to Nathaniel Jones (SVP, Global Threat Intelligence), Eugene Chua (Principal Analyst), Sam Lister (Senior Security Researcher), Adam Potter (Associate Principal Cyber Analyst)

Appendices

Darktrace model detections

·       Anomalous Connection / Multiple HTTP POSTs to Rare Hostname

·       Anomalous Connection / Rare External SSL Self-Signed

·       Anomalous Connection / Suspicious Self-Signed SSL

·       Compromise / Large Number of Suspicious Successful Connections

·       Compromise / Suspicious Beaconing Behaviour

·       Compromise / Agent Beacon to New Endpoint

·       Compromise / Beacon to Young Endpoint

·       Compromise / SSL Beaconing to Rare Destination

·       Compromise / Suspicious TLS Beaconing To Rare External

·       Compromise / Possible Tunnelling to Bin Services

·       Device / Anomalous Github Download

·       Device / Anomalous Package Download

·       Device / Initial Attack Chain Activity

Indicators of compromise (IoCs)

nginxmysql[.]com

45.153.126[.]223

213.111.150[.]145

wisp-agent

85.11.167[.]52

43.98.196[.]73

192.121.47[.]20

www[.]ddduuuppp[.]com

89.46.234[.]50

sqlserver-sqlite[.]com

199.19.95[.]66

graphics-hook-filter64.dll

graphics-hook_config.bin

References

1.      Google. GTIG AI Threat Tracker - https://cloud.google.com/blog/topics/threat-intelligence/agentic-threat-activity-crosses-a-significant-threshold

2.      Federal Bureau of Investigation, Threat Overview of ARTEX Autonomous Penetration Testing Framework, FLASH-20261113-001, 13 November 2026: https://www.ic3.gov/CSA/2026/261113.pdf

3.      Microsoft Security Blog, Storm-0940 Uses ARTEX Agentic AI in ConnectWise Supply Chain Compromise: https://www.microsoft.com/en-us/security/blog/2026/10/21/storm-0940-uses-artex-agentic-ai-connectwise-supply-chain-compromise/

4.      CrowdStrike, VAPOR PANDA Uses ARTEX to Scale Global Campaign: https://www.crowdstrike.com/en-us/blog/vapor-panda-uses-artex-to-scale-global-campaign/

5.      Bitdefender, SilkParasite: Tracking a China-Nexus APT Across Central Asia: https://www.bitdefender.com/en-us/blog/businessinsights/silkparasite-tracking-china-nexus-apt-across-central-asia

‍

‍

Continue reading
About the author
Nathaniel Jones
SVP, Global Threat Intelligence

Blog

/

AI

/

November 18, 2026

Darktrace qualifies for NATO’s Cybersecurity Dynamic Marketplace

Default blog imageDefault blog image

Darktrace has been selected to join NATO’s Cybersecurity Dynamic Marketplace (CSDM), an initiative designed to give NATO faster, more flexible access to cybersecurity technology and services in support of its missions.  

Established by the NATO Communications and Information Agency (NCIA), the marketplace brings together qualified suppliers whose technical capabilities have been reviewed, helping NATO match specialist expertise to project needs and respond more quickly to changing operational priorities.

Qualified across all eight cybersecurity categories

The program’s first phase, known as Lot 1, covers eight cybersecurity categories. Suppliers can qualify in individual categories; Darktrace has qualified to compete for future work across all eight:

  • Identity, Credential and Access Management
  • Endpoint Protection and Platforms
  • Network and Perimeter Security
  • Cloud Security
  • Threat Detection and Analytics Platforms
  • Vulnerability and Exposure Management
  • Digital Forensics and Evidence Platforms
  • Professional Services

Darktrace’s qualification across all eight categories reflects the breadth of our technology and services.

Supporting government and defense organizations

Nation-state attacks, compromised suppliers, the rapid exploitation of security weaknesses and attackers’ growing use of AI are increasing pressure on public-sector organizations. At the same time, agencies are adopting cloud services, connecting the technology that runs physical operations, and introducing automation and AI. Security teams must manage these changes while keeping essential operations running and sensitive information secure.

Protecting these environments requires an understanding of how people, AI and connected systems interact, and the ability to recognize when their activity creates risk. Threats can span several systems, making it essential for security teams to connect related activity and respond quickly.

The Darktrace Behavioral Defense Platform™ supports this approach through unified visibility, continuous behavioral monitoring and autonomous response across AI, people and infrastructure.

At its core, Darktrace’s Adaptive AI™ continuously learns how each organization behaves, building a unique understanding of its people, AI agents and connected systems. This enables the platform to help identify activity that does not belong, connect related behavior across the organization, and investigate and respond to threats autonomously in real time, helping prevent disruption to essential operations.

Our selection builds on work to meet government security requirements internationally. Darktrace recently completed an independent assessment under Australia’s InfoSec Registered Assessors Program (IRAP) for Darktrace / NETWORK™ and Darktrace / OT™ against the Australian Government’s Information Security Manual PROTECTED-level controls. In the United States, Darktrace Federal continues to deliver the Darktrace technology to Department of War, Department of State, and Federal civilian organizations via its on-premises and FedRAMP CLASS D (High) Authorization platforms.

Together, these achievements demonstrate Darktrace’s ability to meet rigorous public-sector security requirements and reinforce its position as a trusted provider of mission-critical cybersecurity technology for government environments.

Meet us at NATO Edge 2026

Darktrace representatives will attend NATO Edge 2026, NCIA’s flagship technology event, in İzmir, Türkiye, from 17 to 19 November. We look forward to meeting government, military, and industry partners to discuss their cybersecurity priorities and how we can support them.

To learn more about the Darktrace Behavioral Defense Platform, visit the platform hub.

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