OpenAI recently disclosed the details of how one of its AI models escaped a sandboxed environment and attacked Hugging Face during an evaluation – and as part of the incident, the models created a messaging board to communicate with each other and influence each other’s reasoning.
OpenAI has now disclosed that shortly after this incident, agents undergoing testing again escaped their ‘secured’ environment and hijacked an obscure German wiki to use as a messaging board. Per Reuters, OpenAI leadership kept the incident hidden while they dealt with the fallout from the Hugging Face incident.
Now that OpenAI has acknowledged its role in the incident, the company has said it is “past time” to put together an incident disclosure pipeline when its models escape testing and slip into third-party networks.
Read more…
Source: TechRadar News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- INTERPOL campaign warns against cyber and financial crimes
December 3, 2024
INTERPOL has launched a campaign to raise awareness on the growing threat of cyber and financial crimes against vulnerable individuals and organizations. The Think Twice campaign, which includes a series of short videos, focuses on five rising online threats: ransomware attacks, malware attacks, phishing, generative AI scams, and romance baiting. These sophisticated scams have seen a ...
- Singapore cyber defenders fight simulated attacks on AI-enabled systems in 4-day exercise
November 15, 2024
More technology is moving onto the cloud – meaning its data is hosted on remote servers rather than on personal devices – and integrating artificial intelligence (AI), which opens it up to new kinds of malicious attacks. To improve Singapore’s ability to counter these emerging threats, soldiers from the Singapore Armed Forces (SAF) and civilians from ...
- ModeLeak: Privilege Escalation to LLM Model Exfiltration in Vertex AI
November 12, 2024
In the race to gain a competitive edge, organizations are increasingly training artificial intelligence (AI) models on sensitive data. But what if a seemingly harmless AI model became a gateway for attackers? A malicious actor could upload a poisoned model to a public repository, and without realizing it, your team could deploy it in your environment. ...
- Gartner Survey Shows AI Enhanced Malicious Attacks as Top Emerging Risk
November 6, 2024
Survey of 286 Senior Enterprise Risk Executives Reveals Top Five Emerging Risks in the Third Quarter of 2024 Artificial intelligence (AI)-enhanced malicious attacks are the top emerging risk for enterprises in the third quarter of 2024, according to Gartner, Inc. It’s the third consecutive quarter with these attacks being the top of emerging risk. IT vendor ...
- Loose-lipped neural networks and lazy scammers
October 31, 2024
One topic being actively researched in connection with the breakout of LLMs is capability uplift – when employees with limited experience or resources in some area become able to perform at a much higher level thanks to LLM technology. This is especially important in information security, where cyberattacks are becoming increasingly cost-effective and larger-scale, causing ...
- New Tradecraft of Iranian Cyber Group Aria Sepehr Ayandehsazan aka Emennet Pasargad
October 30, 2024
The Federal Bureau of Investigation (FBI), U.S. Department of Treasury, and Israel National Cyber Directorate are releasing this Cybersecurity Advisory (CSA) to warn network defenders of new cyber tradecraft of the Iranian cyber group Emennet Pasargad, which has been operating under the company name Aria Sepehr Ayandehsazan (ASA) and is known by the private sector ...