Blog
/
AI
/
December 20, 2022

How to Select the Right Cybersecurity AI

Choosing the right cybersecurity AI is crucial. Darktrace's guide provides insights and tips to help you make an informed decision.
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
Germaine Tan
VP, Security & AI Strategy, Field CISO
Default blog image
20
Dec 2022

AI has long been a buzzword – we started seeing it utilized in consumer space; in social media, e-commerce, and even in our music preference! In the past few years it has started to make its way through the enterprise space, especially in cyber security.

Increasingly, we see threat actors utilizing AI in their attack techniques. This is inevitable with the advancements in AI technology, the lower barrier to entry to the cyber security industry, and the continued profitability of being a threat actor. Surveying security decision makers across different industries like financial services and manufacturing, 77% of the respondents expect weaponized AI to lead to an increase in the scale and speed of attacks. 

Defenders are also ramping up their use of AI in cyber security – with more than 80% of the respondents agreeing that organizations require advanced defenses to combat offensive AI – resulted in a ‘cyber arms race’ with adversaries and security teams in constant pursuit of the latest technological advancements.  

The rules and signature approach is no longer sufficient in this evolving threat landscape. Because of this collective need, we will continue to see the push of AI innovations in this space as well. By 2025, cyber security technologies will account for 25% of the AI software market.

Despite the intrigue surrounding AI, many people have a limited understanding of how it truly works. The mystery of AI technology is what piques the interest of many cyber security practitioners. As an industry we also know that AI is necessary for advancement, but there is so much noise around AI and machine learning that some teams struggle to understand it. The paradox of choice leaves security teams more frustrated and confused by all the options presented to them.

Identifying True AI

You first need to define what you want the AI technology to solve. This might seem trivial, but many security teams often forget to come back to the fundamentals: what problem are you addressing? What are you trying to improve? 

Not every process needs AI; some processes will simply need automation – these are the more straightforward parts of your business. More complex and bigger systems require AI. The crux is identifying these parts of your business, applying AI and being clear of what you are going to achieve with these AI technologies. 

For example, when it comes to factory floor operations or tracking leave days of employees, businesses employ automation technologies, but when it comes to business decisions like PR strategies or new business exploration, AI is used to predict trends and help business owners make these decisions. 

Similarly, in cyber security, when dealing with known threats such as known malicious malware and hosting sites, automation is great at keeping track of them; workflows and playbooks are also best assessed with automation tools. However, when it comes to unknown unknowns like zero-day attacks, insider threats, IoT threats and supply chain attacks, AI is needed to detect and respond these threats as they emerge.

Automation is often communicated as AI, and it becomes difficult for security teams to differentiate. Automation helps you to quickly make a decision you already know you will make, whereas true AI helps you make a better decision.

Key ways to differentiate true AI from automation:

  • The Data Set: In automation, what you are looking for is very well-scoped. You already know what you are looking for – you are just accelerating the process with rules and signatures. True AI is dynamic. You no longer need to define activities that deserve your attention, the AI highlights and prioritizes this for you.
  • Bias: When you define what you are looking for, as humans inherently we impose our biases on these decisions. We are also limited by our knowledge at that point in time – this leaves out the crucial unknown unknowns.‍
  • Real-time: Every organization is always changing and it is important that AI takes all that data into consideration. True AI that is real time and also changes with your organization’s growth is hard to find. 

Our AI Research Centre has produced numerous papers on the applications of true AI in cyber security. The Centre comprises of more than 150 members and has more than 100 patents and patents pending. Some of the featured white papers include research on Attack Path Modeling and using AI as a preventative approach in your organization. 

Integrating AI Outputs with People, Process, and Technology


Integrating AI with People

We are living in the time of trust deficit, and that applies to AI as well. As humans we can be skeptical with AI, so how do we build trust for AI such that it works for us? This applies not only to the users of the technology, but the wider organization as well. Since this is the People pillar, the key factors to achieving trust in AI is through education, culture, and exposure. In a culture where people are open to learn and try new AI technologies, we will naturally build trust towards AI over time.

Integrating AI with Process

Then we should consider the integration of AI and its outputs into your workflow and playbooks. To make decisions around that, security managers need to be clear what their security priorities are, or which security gaps a particular technology is meant to fill. Regardless of whether you have an outsourced MSSP/SOC team, 50-strong in-house SOC team, or even just a 2-man team, it is about understanding your priorities and assigning the proper resources to them.

Integrating AI with Technology 

Finally, there is the integration of AI with your existing technology stack. Most security teams deploy different tools and services to help them achieve different goals – whether it is a tool like SIEM, a firewall, an endpoint, or services like pentesting, or vulnerability assessment exercises. One of the biggest challenges is putting all of this information together and pulling actionable insights out of them. Integration on multiple levels is always challenging with complex technologies because they technologies can rate or interpret threats differently.

Security teams often find themselves spending the most time making sense of the output of different tools and services. For example, taking the outcomes from a pentesting report and trying to enhance SOAR configurations, or looking at SOC alerts to advise firewall configurations, or taking vulnerability assessment reports to scope third-party Incident Response teams.

These tools can have a strong mastery of large volumes of data, but eventually ownership of the knowledge should still lie with the human teams – and the way to do that is with continuous feedback and integration. It is no longer efficient to use human teams to carry out this at scale and at speed. 

The Cyber AI Loop is Darktrace’s approach to cyber security. The four product families make up a key aspect of an organization’s cyber security posture. Darktrace PREVENT, DETECT, RESPOND and HEAL each feed back into a continuous, virtuous cycle, constantly strengthening each other’s abilities. 

This cycle augments humans at every stage of an incident lifecycle. For example, PREVENT may alert you to a vulnerability which holds a particularly high risk potential for your organization. It provides clear mitigation advice, and while you are on this, PREVENT will feed into DETECT and RESPOND, which are immediately poised to kick in should an attack occur in the interim. Conversely, once an attack has been contained by RESPOND, it will feed information back into PREVENT which will anticipate an attacker’s likely next move. Cyber AI Loop helps you harden security a holistic way so that month on month, year on year, the organization continuously improves its defensive posture. 

Explainable AI

Despite its complexity, AI needs to produce outputs that are clear and easy to understand in order to be useful. In the heat of the moment during a cyber incident, human teams need to quickly comprehend: What happened here? When did it happen? What devices are affected? What does it mean for my business? What should I deal with first?

To this end, Darktrace applies another level of AI on top of its initial findings that autonomously investigates in the background, reducing a mass of individual security events to just a few overall cyber incidents worthy of human review. It generates natural-language incident reports with all the relevant information for your team to make judgements in an instant. 

Figure 1: An example of how Darktrace filters individual model breaches into incidents and then critical incidents for the human to review 

Cyber AI Analyst does not only take into consideration network detection but also in your endpoints, your cloud space, IoT devices and OT devices. Cyber AI Analyst also looks at your attack surface and the risks associated to triage and show you the most prioritized alerts that if unexpected would cause maximum damage to your organization. These insights are not only delivered in real time but also unique to your environment.

This also helps address another topic that frequently comes up in conversations around AI: false positives. This is of course a valid concern: what is the point of harvesting the value of AI if it means that a small team now must look at thousands of alerts? But we have to remember that while AI allows us to make more connections over the vastness of logs, its goal is not to create more work for security teams, but to augment them instead.

To ensure that your business can continue to own these AI outputs and more importantly the knowledge, Explainable AI such as that used in Darktrace’s Cyber AI Analyst is needed to interpret the findings of AI, to ensure human teams know what happened, what action (if any) the AI took, and why. 

Conclusion

Every organization is different, and its security should reflect that. However, some fundamental common challenges of AI in cyber security are shared amongst all security teams, regardless of size, resources, industry vertical, and culture. Their cyber strategy and maturity levels are what sets them apart. Maturity is not defined by how many professional certifications or how many years of experience the team has. A mature team works together to solve problems. They understand that while AI is not the silver bullet, it is a powerful bullet that if used right, will autonomously harden the security of the complete digital ecosystem, while augmenting the humans tasked with defending it. 

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
Germaine Tan
VP, Security & AI Strategy, 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.

Figure 3: Darktrace's Real-Time AI Analyst investigation showing a server making repeated HTTP requests, using a curl user agent, to a rare external endpoint on port 8099.

‍

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 4: 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 5: Darktrace Advanced Search showing Azure AD operation names associated with the activity.

‍

Figure 6: Darktrace Advanced Search showing the Azure Resource Manager action used to execute scripts.
Figure 7: 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.

In some of these cases, Darktrace's Autonomous Response took or recommended action against the activity, including blocking internal connectivity over specified ports, inhibiting outbound connections with likely C2 endpoints, and/or disabling SaaS/IaaS user accounts. While many of these recommended actions required human confirmation due to deployment configuration preferences, had these actions been applied autonomously at the time of alert, the scope of activity would have been limited, thereby giving analysts time to investigate and respond.

‍

Figure 8: Autonomous Response blocking suspicious firewall modification activity.

‍

Figure 9: Autonomous Response summary for affected cloud users during the intrusion.

‍

Figure 10: Autonomous Response taking action against unusual lateral movement activity on an affected device.

‍

Figure 12: Autonomous Response summary for affected network users during the time of the intrusion.

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. Containing abnormal activity at machine speed can stop an intrusion progressing while analysts establish impact and its extent. Autonomous Response does not replace that human analysis, but rather augments defender teams' capabilities by extending the window for investigation.

‍

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

Edited by Ryan Traill (Content Manager)

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