Today's cybersecurity headlines are brought to you by ThreatPerspective


Ethical Hacking News

ARTEX Framework: The Key to Cybercriminals' AI-Powered Attacks


Recent reports have highlighted the use of the ARTEX framework in AI-powered cyberattacks, with attackers using deepfakes and reverse-engineering techniques to evade detection. The attacks took advantage of basic security weaknesses, including default passwords, exposed API keys, and outdated software. Organizations must prioritize security measures and ensure that AI applications and systems receive adequate security protections to prevent such attacks.

  • Artificial Intelligence (AI) agents are being used by cybercriminals to automate attacks and scale their operations.
  • The ARTEX framework is an open-source agentic AI penetration testing framework used by attackers to test vulnerabilities in software and networks.
  • ARTEX agents have been spotted stealing AI credentials and testing deepfake ID bypasses, evading detection with sophisticated techniques.
  • Attacks exploited basic security weaknesses, including default passwords, exposed API keys, and outdated software.
  • Organizations must prioritize security measures, monitor unexpected costs and unusual usage, and ensure AI applications receive the same security protections as other production systems.



  • In the ever-evolving landscape of cybersecurity threats, the use of Artificial Intelligence (AI) agents has become a significant factor in the success of cybercriminals. The recent reports of attacks using the ARTEX framework, an open-source agentic AI penetration testing framework, have shed light on the capabilities and tactics employed by these attackers.

    The ARTEX framework is designed to provide a platform for AI agents to operate, allowing them to automate various tasks and scale their attacks. This framework is particularly useful for cybercriminals looking to exploit vulnerabilities in software and networks, as it enables them to test a wide range of scenarios and identify potential entry points.

    According to Amazon's threat intelligence team, ARTEX agents have been spotted running on the ARTEX framework, stealing AI credentials and testing deepfake ID bypasses. These agents were able to evade detection by using sophisticated techniques, such as generating real-time deepfakes to pass live selfie checks and forging ID document photos to pass document checks.

    The agents also reverse-engineered one vendor's liveness check, which confirms a living person is present, and documented its face-detection events and coordinate system. They worked on ID photos too, building fake camera metadata matching the real image dimensions and keeping the original compression tables that re-saving would normally replace, so an edited image looked like an untouched camera photo at file level.

    The attacks took advantage of basic security weaknesses, including default passwords, exposed API keys, open interfaces, and outdated software. The agents succeeded where basic security hygiene was missing, including default or hardcoded credentials, keys left in code and public artifacts, unauthenticated interfaces and inference endpoints, and unpatched software.

    Amazon's threat intelligence team assessed threat activity referencing potentially affected AWS customers and notified them as appropriate. However, the company could not confirm whether other organizations had been targeted.

    The report highlights the importance of getting the fundamentals right when it comes to security. "None of the techniques in these campaigns were new," the report concludes. "What AI agents change is the speed and persistence of the attacker. The agents succeeded where basic security hygiene was missing, including default or hardcoded credentials, keys left in code and public artifacts, unauthenticated interfaces and inference endpoints, and unpatched software."

    In light of these findings, it is essential for organizations to prioritize security measures, such as monitoring unexpected costs and unusual usage, and to ensure that AI applications, model gateways, and inference endpoints receive the same security protections as other production systems.

    The use of AI agents in cybercriminal activities is a growing concern, and it is crucial for organizations to stay vigilant and take proactive measures to prevent such attacks. By understanding the tactics and techniques employed by these attackers, organizations can better prepare themselves to defend against future threats.



    Related Information:
  • https://www.ethicalhackingnews.com/articles/ARTEX-Framework-The-Key-to-Cybercriminals-AI-Powered-Attacks-ehn.shtml

  • https://securityaffairs.com/203188/ai/artex-how-cybercriminals-use-ai-agents-to-scale-their-attacks.html


  • Published: Mon Nov 16 04:14:04 2026 by llama3.2 3B Q4_K_M













    © Ethical Hacking News . All rights reserved.

    Privacy | Terms of Use | Contact Us