Blog
/
AI
/
junio 10, 2026

Cómo proteger la IA en la empresa: un marco práctico para modelos, datos y agentes

La IA avanza a un ritmo más rápido del que la gobernanza puede seguir, lo que amplía las superficies de ataque y genera riesgos hasta ahora desconocidos. Desde los datos y los modelos hasta los agentes de IA y las integraciones, la seguridad comienza por saber qué hay que proteger. Descubra cómo identificar los riesgos derivados de la IA, de modo que pueda establecer marcos de gobernanza y controles que protejan la innovación sin exponer a la empresa a nuevas superficies de ataque. 
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
Brittany Woodsmall
Senior Product Marketing Manager, AI
Written by
Simon Fellows
Senior Vice President, Product Strategy
How to secure AI in the enterprise: A practical framework for models, data, and agents Default blog image
10
jun 2026

Conclusiones clave

  • La seguridad de la IA en la empresa va más allá de proteger los modelos de IA: también implica proteger los agentes de IA, los datos empresariales, las identidades, las API y las integraciones de terceros. Las organizaciones necesitan visibilidad sobre dónde se implementa la IA, a qué puede acceder y cómo se comporta para gestionar eficazmente el riesgo de la IA.
  • Un marco eficaz de seguridad de la IA combina la gobernanza, la gestión de identidades y accesos, la protección de datos, la supervisión en tiempo de ejecución y la seguridad de la cadena de suministro de software. Ningún control ni ninguna salvaguarda de IA bastan por sí solos para proteger la IA empresarial.
  • La adopción y la seguridad de la IA deben evolucionar a la par. Integrar controles de seguridad en todo el ciclo de vida de la IA permite a las organizaciones reducir el ciberriesgo, respaldar el cumplimiento normativo y escalar las iniciativas de IA con mayor confianza.

¿Por qué es ahora prioritaria la seguridad de la IA en la empresa?

Proteger la IA empresarial es ahora una prioridad porque su adopción avanza más rápido que la gobernanza, la asignación de responsabilidades y los controles técnicos. Las herramientas de IA generativa, las funciones de IA integradas y los agentes autónomos pueden acceder a datos confidenciales, tomar decisiones y conectarse a sistemas externos, lo que genera riesgos relacionados con la seguridad, la privacidad, el cumplimiento normativo y las operaciones. Para muchas organizaciones, el primer reto no es si deben proteger la IA, sino qué significa realmente «proteger la IA» en la práctica. ¿Se trata de proteger los modelos? ¿Gobernar los datos? ¿Supervisar los resultados? ¿O controlar cómo se comportan los agentes de IA una vez implementados?  

Mientras aumenta la demanda de adopción, proteger el uso de la IA en la empresa sigue siendo un concepto abstracto para muchos, y poner en práctica su uso va mucho más allá de tener visibilidad. Los profesionales también deben tener en cuenta cómo se adquiere, desarrolla, implementa, utiliza y gobierna la IA en toda la empresa.

El objetivo de los equipos de seguridad: implementar un marco de seguridad de la IA basado en el ciclo de vida. Esta entrada de blog mostrará la variedad de casos de uso de la IA que deben tenerse en cuenta al desarrollar este marco y cómo plantear esta conversación a públicos no técnicos.  

¿Qué significa proteger la IA en la empresa?

Proteger la IA implica mantener la visibilidad y el control sobre dónde se utiliza, a qué datos accede, cómo se comportan los modelos y los agentes, y si sus acciones se ajustan a los objetivos empresariales. Abarca aplicaciones, identidades, infraestructura, datos, flujos de trabajo de desarrollo y terceros, por lo que la responsabilidad no puede recaer únicamente en una función de seguridad.

La seguridad de la IA suele plantearse como una extensión de las disciplinas de seguridad existentes. En la práctica, esta suposición puede generar confusión.

Las funciones de seguridad tradicionales se basan en límites relativamente estables. La seguridad de las aplicaciones se centra en el código y la lógica. La seguridad en la nube gestiona la infraestructura y la identidad. La seguridad de los datos protege la información confidencial tanto en reposo como en tránsito. La seguridad de la identidad controla quién puede acceder a los sistemas y servicios. Cada función cuenta con responsabilidades claramente definidas, herramientas establecidas y modos de fallo bien conocidos.

La IA no encaja perfectamente en ninguna de estas categorías. Un sistema de IA es, a la vez:

  • Una aplicación que ejecuta lógica
  • Un procesador de datos que recopila y genera información confidencial
  • Una capa de toma de decisiones que influye en las acciones o las automatiza
  • Un sistema dinámico que cambia su comportamiento con el tiempo

Por consiguiente, los riesgos de seguridad que introduce la IA abarcan varios ámbitos a la vez. Una sola interacción con IA puede implicar un uso indebido de identidades, exposición de datos, abuso de la lógica de las aplicaciones y riesgos en la cadena de suministro, todo dentro del mismo flujo de trabajo. Es aquí donde empiezan a difuminarse las líneas tradicionales entre las funciones de seguridad.

Por ejemplo, un prompt malicioso enviado por un usuario autorizado no constituye una vulneración de identidad clásica, pero puede provocar una filtración de datos o acciones no autorizadas. Un agente de IA que llama a un servicio externo puede parecer una acción legítima de una aplicación, aunque infrinja la soberanía de los datos o los requisitos de cumplimiento normativo. El código generado por IA puede superar las comprobaciones de desarrollo estándar y, aun así, introducir vulnerabilidades sutiles o dependencias comprometidas.

En ninguno de estos casos el riesgo «pertenece» por completo a un solo equipo de seguridad.

Por eso, la protección de la IA no puede limitarse a la seguridad de los modelos, las políticas de gobernanza o los controles perimetrales. Requiere una perspectiva de seguridad compartida que abarque el desarrollo, las operaciones, el tratamiento de datos y la interacción con los usuarios. Proteger la IA significa comprender no solo si se accede a los sistemas de forma segura, sino también si se utilizan, se entrenan y se les permite actuar de maneras que se ajusten a los objetivos empresariales y a la tolerancia al riesgo.

En esencia, proteger la IA consiste en recuperar la claridad en entornos donde la rendición de cuentas puede difuminarse rápidamente. Se trata de saber dónde está presente la IA, cómo se comporta, qué tiene permitido hacer y cómo afectan sus decisiones al conjunto de la empresa. Sin esta claridad, la IA se convierte en un multiplicador tanto de la productividad como del riesgo.

¿Qué debe abarcar un marco de seguridad de la IA empresarial?

Un marco de seguridad de la IA empresarial debe abordar el uso indebido y el comportamiento emergente, la supervisión en tiempo de ejecución, el desarrollo y la infraestructura, la IA en la sombra y las cadenas de suministro de terceros, así como la preparación organizativa. En conjunto, estas áreas abarcan cómo se adquiere, desarrolla, implementa, supervisa y gobierna la IA a lo largo de su ciclo de vida, y cómo se accede a ella.

Hay cinco áreas clave para proteger la IA en la empresa:

  • Prevención del uso indebido y de los comportamientos emergentes de la IA
  • Supervisión y control de la IA en funcionamiento
  • Protección del desarrollo e infraestructura de la IA
  • Seguridad de la cadena de suministro de IA
  • Fortalecimiento de la preparación y la supervisión

En conjunto, estas categorías ofrecen un enfoque estructurado para comprender cómo se manifiesta el riesgo de la IA y dónde deben centrar sus esfuerzos los equipos de seguridad.

1. Prevención del uso indebido y de los comportamientos emergentes de la IA

Los sistemas y agentes de IA generativa pueden manipularse de formas que eluden los controles tradicionales. Aunque el acceso esté autorizado, se puede hacer un uso indebido de la IA, reutilizarla para otros fines o influir en ella mediante prompts e interacciones cuidadosamente elaborados.

Entre los principales riesgos se incluyen:

  • Inyección maliciosa de prompts diseñada para forzar acciones no deseadas
  • Casos de uso no autorizados o no intencionados que eluden las salvaguardas
  • Exposición de datos confidenciales a través de los historiales de prompts
  • Alucinaciones o resultados maliciosos que influyen en el comportamiento humano

A diferencia de las aplicaciones tradicionales, los sistemas de IA pueden generar resultados perjudiciales sin estar explícitamente comprometidos. Proteger esta capa requiere supervisar la intención, no solo el acceso. Los equipos de seguridad necesitan visibilidad sobre cómo se envían prompts a los sistemas de IA, cómo se consumen los resultados y si el uso se ajusta a los fines empresariales aprobados

2. Supervisión y control de la IA en funcionamiento

Una vez implementados, los agentes de IA operan a velocidad y escala de máquina. Pueden iniciar acciones, intercambiar datos e interactuar con otros sistemas con poca supervisión humana. Por ello, la visibilidad en tiempo de ejecución resulta fundamental.

Los riesgos operativos de la IA incluyen:

  • Agentes que utilizan permisos de formas no previstas
  • Conexiones salientes no controladas a servicios o agentes externos
  • Pérdida de visibilidad forense sobre componentes efímeros de IA
  • Transmisión de datos entre jurisdicciones que incumple la normativa

Proteger la IA en funcionamiento requiere la supervisión en tiempo real del comportamiento de los agentes, puntos de control centralizados como gateways de IA y la capacidad de capturar el estado del agente para su investigación. Sin estas capacidades, los equipos de seguridad pueden carecer de visibilidad sobre cómo se comportan los sistemas de IA una vez en funcionamiento, especialmente en entornos nativos de la nube o regulados.

3. Protección del desarrollo e infraestructura de la IA

Muchos riesgos de la IA surgen mucho antes de la implementación. Las canalizaciones de desarrollo, las configuraciones de infraestructura y las decisiones arquitectónicas influyen en la postura de seguridad de los sistemas de IA.

Entre los riesgos habituales se incluyen:

  • Permisos y mecanismos de control mal configurados
  • Arquitecturas de agentes inseguras o excesivamente complejas
  • Infraestructura como código que introduce configuraciones incorrectas silenciosas
  • Vulnerabilidades en el código generado por IA y en las dependencias

El código generado por IA añade una nueva dimensión de riesgo, ya que los paquetes alucinados o la lógica poco segura pueden ser más difíciles de detectar y depurar que el código escrito por personas. Proteger el desarrollo de la IA implica aplicar controles de seguridad desde el principio, incluidos el análisis estático, la revisión de la arquitectura y la supervisión continua de la configuración a lo largo de todo el proceso de compilación.

4. Seguridad de la cadena de suministro de IA

Las cadenas de suministro de IA suelen ser opacas. Los modelos, conjuntos de datos, dependencias y servicios pueden proceder de terceros con distintos niveles de transparencia y garantías.

Riesgos clave de la cadena de suministro:

  • Herramientas de IA en la sombra utilizadas fuera de los controles aprobados
  • Agentes de IA externos con acceso interno
  • Proveedores que aplican IA a datos empresariales sin informar de ello
  • Modelos, datos de entrenamiento o dependencias comprometidos

Proteger la cadena de suministro de IA requiere descubrir dónde se utiliza la IA, validar la procedencia y las licencias de los modelos y los datos, y evaluar cómo procesan y protegen los proveedores la información de la empresa. Sin esta visibilidad, las organizaciones se exponen a fugas de datos, a riesgos regulatorios y a la vulneración de sistemas posteriores a través de integraciones de confianza.

5. Fortalecimiento de la preparación y la supervisión

Aunque existan controles técnicos sólidos, la seguridad de la IA falla sin gobernanza, pruebas y equipos formados. La IA plantea nuevos escenarios de incidentes que muchos equipos de seguridad aún no están preparados para gestionar.

Los riesgos de supervisión incluyen:

  • Falta de informes significativos sobre los riesgos de la IA
  • Sistemas de IA no probados en producción
  • Equipos de seguridad sin formación sobre amenazas específicas de la IA

Las organizaciones necesitan informes que tengan en cuenta la IA, ejercicios de equipos rojos y morados que incluyan sistemas de IA y formación continua para desarrollar la preparación operativa. Estas capacidades garantizan que los riesgos de la IA se comprendan, se pongan a prueba y se gestionen cada vez mejor, en lugar de descubrirse en pleno incidente.

Un nuevo enfoque de la seguridad de la IA para los consejos de administración

La seguridad de la IA no es solo una cuestión técnica. Es una cuestión de confianza, responsabilidad y resiliencia. Los consejos de administración quieren tener la garantía de que las decisiones basadas en IA son fiables, explicables y están protegidas contra manipulaciones.

La comunicación eficaz con la dirección se centra en:

  • Confianza: certeza sobre la integridad de los datos, el comportamiento de los modelos y los resultados
  • Rendición de cuentas: responsabilidades claramente definidas entre equipos y proveedores
  • Resiliencia: la capacidad de operar, auditar y adaptarse ante un ataque o una regulación

Vincular los esfuerzos de seguridad de la IA a marcos reconocidos, como la ISO/IEC 42001 y el Marco de Gestión de Riesgos de la IA del NIST, ayuda a demostrar madurez y alinea la seguridad de la IA con objetivos de gobernanza más amplios.

Conclusión: proteger la IA es un desafío que abarca todo el ciclo de vida

Las mismas características que hacen que la IA sea transformadora también dificultan su protección. Los sistemas de IA difuminan los límites tradicionales entre el software, los usuarios y la toma de decisiones, lo que amplía la superficie de ataque de formas sutiles pero significativas.

Garantizar la seguridad de la IA requiere recuperar la claridad. Saber dónde está presente la IA, cómo se comporta, quién la controla y cómo se gobierna. Un enfoque basado en marcos de trabajo permite a las organizaciones innovar con IA y, al mismo tiempo, mantener la confianza, la rendición de cuentas y el control.

El camino hacia una IA segura es un proceso continuo, pero comienza por comprender los riesgos a lo largo de todo el ciclo de vida de la IA y desarrollar prácticas de seguridad que evolucionen junto con la tecnología.

Darktrace / SECURE AI respalda este enfoque del ciclo de vida al reunir visibilidad en toda la empresa, supervisión del comportamiento y control en tiempo real, lo que ayuda a los equipos de seguridad a identificar actividades de riesgo y adoptar la IA de forma más segura.

[related-resource]

Descargue el marco de trabajo completo

Descubra cómo identificar los riesgos de la IA para establecer marcos de gobernanza y controles en su organización.

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
Brittany Woodsmall
Senior Product Marketing Manager, AI
Written by
Simon Fellows
Senior Vice President, Product Strategy

More in this series

No items found.

Blog

/

AI

/

noviembre 19, 2026

Microsoft Perception, Agentic Insiders and the Role of Behavioral Security

Default blog imageDefault blog image

This week at Ignite, Microsoft announced that Microsoft Perception is generally available. It is a significant milestone for the industry, and one we welcome as a Microsoft partner. Microsoft is putting an architectural bet at the center of its security strategy: AI has changed the speed of cyber, and defense must change with it.

At Darktrace, we’ve long held the same view, so it’s encouraging to see a partner of Microsoft’s scale articulate it so clearly and bring it to market.

Security gets a team of agents

Perception is Microsoft’s agentic security system. It orchestrates red, blue, and green team agents through playbooks in a closed loop: red agents simulate attacks, blue agents detect, triage and investigate, and green agents fix and remediate. Rather than adding another assistant to the SOC, it creates coordinated teams of agents that share context. Security teams set the guardrails and approve high-impact actions.

Microsoft frames this as a three-layer cyber stack: signals, sensors and actuators; a context layer; and agents, harness and models on top. Together with partner sources, the foundation produces more than 165 trillion signals per day.  

The announcement also makes a second point that matters just as much. Microsoft is treating AI agents themselves as a new insider-risk category. In its words, “Agents are the new insiders.” They work at machine speed, around the clock, with broad access to data, apps, tools and other agents, and like any insider they can make mistakes, be manipulated or be compromised. New capabilities such as Dynamic Agent Risk (now in preview) and dynamic Conditional Access controls are designed to assess and contain that risk as it changes.

Four truths about security in the agentic era

The announcement is built on four ideas, and together they describe the new reality security teams are defending:

  1. Static security can’t keep up. Microsoft validates what many security practitioners have observed; the window between a vulnerability’s discovery and its exploitation is collapsing from months to minutes. Manual triage can’t answer that pace. Autonomous detection and response is now a requirement, not simply a “nice to have”.
  2. Agents must be treated as insiders. The question for security teams is no longer only “who is this user?” but “what is this agent actually doing?” Identity tells you who an agent is. Policy tells you what it is allowed to do. Neither tells you whether its behavior is normal.
  3. Security is moving from signatures to behavior and context. Dynamic Agent Risk looks across identity, data, endpoint, cloud and network signals and asks whether an agent’s actions are drifting from the intent of its task. That is behavioral thinking, and it is philosophically close to the Adaptive AI approach Darktrace has pioneered.
  4. Machine-speed attacks demand machine-speed response. Humans set the objectives and guardrails. Autonomous systems do the work inside them, both detecting and acting. Microsoft’s design has agents investigate, recommend and, within approved boundaries, act, with security teams setting the limits. At this pace, the gap between knowing something is wrong and doing something about it has to close to seconds.

The opportunity: where control plane meets behavioral context

Perception is an extraordinary control plane for agentic security. The question for security leaders is how to make it even more effective in the environments they actually run.

Real enterprises are heterogeneous. They run AWS and Google Cloud alongside Azure, and OT, IoT and third-party identity alongside Entra. Increasingly they also run AI agents and MCP-connected systems that no single vendor’s telemetry fully covers. Microsoft’s architecture recognizes this, with more than 500 connectors into the wider ecosystem.

That is where Darktrace’s role is distinct. The challenge isn’t signal volume, where Microsoft’s scale is unmatched. It’s deeply understanding what is normal for a specific organization, across every system, identity and agent in it. Together, we deliver two complementary layers:

  • Microsoft brings global intelligence and orchestration. It tells you what is known, what it means and what to do about it.
  • Darktrace brings organization-specific behavioral context. It tells you what is unusual here, right now, across the organizations AI, people and infrastructure, even if it has never been seen before.

The difference shows up in the numbers. A large enterprise generates billions of signals. Darktrace turns them into thousands of incidents, narrows those to hundreds of AI-led investigations, and surfaces as few as 20 that merit a human’s attention. For an agentic SOC, that kind of evaluated, prioritized input makes agents faster, not busier.

As enterprises deploy more agents, the hard problem becomes behavior that is technically permitted but unusual, manipulated or inconsistent with the agent’s purpose. Consider an agent that normally reads Salesforce records during US business hours and suddenly starts enumerating SharePoint and opening unusual outbound connections. Each step may use valid access and approved tools, so identity and policy checks can all pass. Spotting it requires knowing the behavior is abnormal for this agent, in this environment, right now.

That is why one principle in Microsoft’s AI Transparency Initiative matters so much: organizations should be able to see what their AI accesses and does, and independently verify those actions.  

  • Identity and permissions answer “should this agent be allowed to do this?”
  • Behavioral defense answers “even though it is allowed, is what it’s doing normal?”

Deterministic controls around non-deterministic AI are the right foundation, and continuously learned baselines are how organizations can verify those controls are working. ‍

What to look for in an agentic SOC architecture

As organizations adopt platforms like Perception, we’d encourage them to look for three capabilities:

  1. Behavioral context in the control plane. Agents work best with high-confidence signals rather than thousands of raw alerts: here is the behavior that materially deviates from this organization’s learned normal.
  2. ‍Behavioral reasoning on demand. During an investigation, agents should be able to ask what changed around a given identity, device or agent in the last 24 hours, and get a clear answer. ‍
  3. Autonomous, coordinated response across the stack. Response should be as fast as the threat without being reckless: acting immediately when confidence is high, constraining or reversing actions when it isn’t, and keeping a human in the loop when it matters. Within policy and human-approval guardrails, it should target the abnormal behavior rather than the whole business process and span identity, endpoint and the wider environment.

These are the areas where we’re focused, and where we look forward to working with Microsoft and the broader ecosystem.

Response is where speed is won or lost

In the AI era, detection and investigation only matter if action follows quickly. Perception brings agentic orchestration to that problem, with security teams setting the guardrails and approving high-impact steps. Autonomous response from Darktrace takes a complementary approach: it responds on behavioral deviation, in a way that is proportionate and targeted. It can interrupt activity that is abnormal for that specific device, identity or agent while leaving normal business activity running.

The two approaches fit together naturally. Behavioral signals can tell an orchestration layer that something has changed and how confident the system is. Orchestrated playbooks can then coordinate wider containment across identity, endpoint and cloud, within the policies customers define.

The bigger picture

The industry’s architecture is converging on identity, policy, telemetry, behavior, autonomous reasoning and machine-speed response. Microsoft is building formidable pieces of that picture, especially identity, policy, telemetry and orchestration.

Behavior is the layer Darktrace is built to provide: an independent intelligence that continuously learns how humans, machines and AI agents normally act, detects the moment reality departs from intent, and can respond to that deviation in a targeted, proportionate way that keeps normal business running. When attacks move at machine speed, understanding what is abnormal and acting on it quickly have to go together.

Perception brings together what Microsoft knows and orchestrates the response across its stack. Darktrace helps organizations understand what is normal for them and act on what isn’t. Customers building their agentic security strategy will need both.

Congratulations to our partners at Microsoft on this milestone. We look forward to helping customers secure the agentic era together.

Learn more about Darktrace Behavioral Defense.

Continue reading
About the author
Kellie Regan
Director, Product Marketing - Cloud Security

Blog

/

AI

/

noviembre 19, 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: Autonomous Response model alert in due to the identification of multiple underlying lateral movement related activities, including spikes in SMB and RPC operations on an affected Ivanti network device during an Artex-supported Vapor Panda intrusion.
Figure 2: Autonomous Response action summary console listing all recommended actions for an affected Ivanti network device following the detection of several underlying anomalous behaviors during the Artex-supported Vapor Panda intrusion.

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.

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 3: Darktrace Advanced Search showing Azure AD operation names associated with the activity.
Figure 4: Darktrace Advanced Search showing the Azure Resource Manager action used to execute scripts.
Figure 5: Darktrace Device Event log window showing the triggered models related to the suspicious Azure activity.
Figure 6: Autonomous Response model alert for affected Azure account during Artex intrusion due to the  unusual source IP for the noted activity and the unexpected privileged operations in the Azure environment.
Figure 7: Autonomous Response action summary console for hijacked cloud Azure Identity following the detection of anomalous SaaS/IaaS actions including key/secret requests and Firewall configuration changes.

‍

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.

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
Your data. Our AI.
Elevate your network security with Darktrace AI