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:
- AI jailbreaks: What they are and how they can be mitigated
June 4, 2024
Generative AI systems are made up of multiple components that interact to provide a rich user experience between the human and the AI model(s). As part of a responsible AI approach, AI models are protected by layers of defense mechanisms to prevent the production of harmful content or being used to carry out instructions that go ...
- 5 Reasons to Attend Cyber Security & Cloud Congress North America 2024
May 24, 2024
Explore the forefront of enterprise technology at the Cyber Security & Cloud Congress North America. Delve into the entirety of the Cyber Security & Cloud Ecosystem and unravel the practical and triumphant application of Cyber Security & Cloud. Returning to North America on June 5-6, 2024, at the esteemed Santa Clara Convention Center, the globally renowned ...
- Why Microsoft’s New AI Feature Has Prompted Privacy Concerns
May 22, 2024
Microsoft introduced a new series of products, named Copilot+ PCs, that are designed to be integrated with artificial intelligence technology in mind. The company has reportedly struggled with the laptop market in recent months, with sales of the flagship surface pro laptops declining significantly in 2023. But the new AI device features have raised privacy concerns. ...
- Deepfake video conference sees criminals escape with US$25 million
May 20, 2024
In February, a multinational company’s finance team member in Hong Kong made headlines after he transmitted HK$200 million (US$25 million) to cybercriminals who pretended to be the chief financial officer and other colleagues, using deepfake technology, in what the worker thought was a legitimate video conference. Now it’s been revealed that it was UK engineering group ...
- SugarGh0st RAT Used to Target American Artificial Intelligence Experts
May 16, 2024
Proofpoint recently identified a SugarGh0st RAT campaign targeting organizations in the United States involved in artificial intelligence efforts, including those in academia, private industry, and government service. Proofpoint tracks the cluster responsible for this activity as UNK_SweetSpecter. SugarGh0st RAT is a remote access trojan, and is a customized variant of Gh0stRAT, an older commodity trojan typically ...
- Washington Takes Its Cyber Strategy Global
May 8, 2024
The United States has spent two years supporting Ukraine in one ground war and seven months backing Israel in another, and it continues to prepare for the possibility of a third in Taiwan. But arguably its most persistent focus has been on a far longer-running, more perennial, borderless battle over cyberspace and the future of technology. ...