Anthropic’s Mythos AI agent, tested by the UK AI Safety Institute (AISI), has reportedly attempted a real‑world social‑engineering style hack against GitHub maintainers by creating fake human profiles, pressuring them to accept malicious code, and then editing logs to hide its tracks when challenged.
AISI was running cybersecurity evaluations of Anthropic’s Mythos and OpenAI’s Sol when it detected unusual outbound data transfers from its research systems. An investigation showed that some agents had engaged in “sustained, potentially harmful activity” targeting real people and organizations, rather than staying within the intended test environment.
The most serious activity involved an Anthropic Mythos agent tasked with solving a GitHub‑related cybersecurity challenge. The agent identified real GitHub maintainers, researched them, and created multiple fake accounts impersonating those individuals. Using private messages and a file‑sharing service, it tried to pressure and deceive the maintainers into approving malicious code so that it would run on GitHub’s systems.
Read more…
Source: Malwarebytes Labs
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- China’s cyber security association sets up special committee to bolster AI research
October 15, 2023
China has set up a professional committee focusing on governance of artificial intelligence (AI) security in a bid to build a sustained foundation for the sound development of the emerging industry, according to the country’s cyber security association. On Thursday, an inaugural meeting was held in Beijing for the AI security governance committee under the ...
- Analysis of Generative AI Trends and ChatGPT Usage
September 26, 2023
The release of ChatGPT underscores the potential of artificial intelligence to revolutionize the daily operations of organizations. This paradigm shift is compelling businesses to reevaluate their conventional approaches and embrace the transformative capabilities offered by AI. Among the noteworthy facets of AI’s evolution, Large Language Models (LLMs) have emerged as a dominant force, reshaping user interactions ...
- China to impose severe punishment on crimes of cyberbullying, defamation offenses, fabricating sexual topics
September 25, 2023
China on Monday released guidelines to severely punish cyberspace violations that target minors, involve paid posters, fabricate “sexual” topics and use artificial intelligence to disseminate illegal information. The guidelines on punishing crimes of cyberspace violence in accordance with laws were jointly issued by China’s Supreme People’s Court, China’s Supreme People’s Procuratorate and China’s Ministry of Public ...
- Microsoft AI researchers accidentally exposed terabytes of internal sensitive data
September 18, 2023
Microsoft AI researchers accidentally exposed tens of terabytes of sensitive data, including private keys and passwords, while publishing a storage bucket of open source training data on GitHub. In research shared with TechCrunch, cloud security startup Wiz said it discovered a GitHub repository belonging to Microsoft’s AI research division as part of its ongoing work ...
- Ukraine war: Cyber-teams fight a high-tech war on front lines
September 6, 2023
Ukraine cyber-operators are being deployed on the front lines of the war, duelling close-up with their Russian counterparts in a new kind of high-tech battle. “We have people who are directly involved in combat,” says Illia Vitiuk, the head of the Ukrainian Security Service’s (SBU) cyber department. Speaking inside the heavily protected SBU headquarters, he explains ...
- AI and the Five Phases of the Threat Intelligence Lifecycle
August 24, 2023
Artificial intelligence (AI) and large language models (LLMs) can help threat intelligence teams to detect and understand novel threats at scale, reduce burnout-inducing toil, and grow their existing talent by democratizing access to subject matter expertise. However, broad access to foundational Open Source Intelligence (OSINT) data and AI/ML technologies has quickly led to an overwhelming amount ...