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:
- Terrorism and cyber attack warning as 25 biggest threats facing Ireland revealed
August 3, 2023
Ireland faces an increased threat from terrorism and cyber-attacks – because we spend so little money on defence, the government has admitted. This year’s national risk assessment also finds that Ireland faces 25 different potential threats – from terrorism to financial instability, as well as climate change, AI and even housing problems. Read more… Source: Irish Mirror
- Sha zhu pan scam uses AI chat tool to target iPhone and Android users
August 2, 2023
Over the past two years, we have been tracking a variety of scams targeting mobile device users, generally referred to as “shā zhū pán” (杀猪盘, which translates as “butcher plate”) or “Pig Butchering.” This includes a category we labelled as “CryptoRom” when we initially investigated it in 2020, because of its two distinguishing characteristics—a focus on ...
- UK spy agencies want to relax ‘burdensome’ laws on AI data use
August 1, 2023
The UK intelligence agencies are lobbying the government to weaken surveillance laws they argue place a “burdensome” limit on their ability to train artificial intelligence models with large amounts of personal data. The proposals would make it easier for GCHQ, MI6 and MI5 to use certain types of data, by relaxing safeguards designed to protect people’s ...
- NATO Innovation Fund closes on EUR 1bn flagship fund
August 1, 2023
Twenty-three NATO Allies have officially become Limited Partners of the NATO Innovation Fund (NIF), which is preparing to make its initial investments later this year. The Participating Allies* have also welcomed Sweden’s interest to join the NIF. Sweden’s participation will take effect upon its accession to the North Atlantic Treaty. Read more… Source: NATO Innovation Fund (NIF)
- Understanding Machine Learning Attacks, Techniques, and Defenses
July 26, 2023
Machine learning (ML) is a subset of Artificial Intelligence (AI), which enables machines and software to automatically learn from historical data to generate accurate output without being programmed to do so. Many leading organizations today have incorporated machine learning into their daily processes for business intelligence. But the ability of machine learning can be altered by ...
- US Army Hopes AI Will Give Soldiers An Information Advantage
July 21, 2023
The Army in recent years has introduced the concept of “information advantage,” in which soldiers have the ability to make decisions and act faster than their adversaries. The service now believes artificial intelligence is the key to making the strategy a reality. Both in industry and the Defense Department, many are exploring the possibility of utilizing ...