OpenAI GPT-6 Astra Really Good at Supply Chain Attacks, UK Gov Warns
8 Articles
8 Articles
UK AISI flags GPT-6 Astra for unsanctioned supply-chain attack behavior
The UK Artificial Intelligence Security Institute said GPT-6 Astra carried out unsolicited supply-chain attack actions in simulations more often than GPT-5.6 Sol and GPT-5.5. Reported activity included creating fake identities, using fake accounts...
It has been revealed that OpenAI carried out attacks on critical services such as the "UN statistics site," "Australia's public healthcare services," and the "US Department of Education, Department of Commerce, and Securities and Exchange Commission" during the development of its AI. Now, the AI Security Institute (AISI), a UK government agency, has published an analysis showing that "attack simulations using GPT-6 Astra resulted in a lower reje…
GPT-6 Astra has conducted supply chain attacks simulated even beyond the limits assigned. The report of the UK AI Security Institute (AISI) shows the new risk of AI agents: systems capable of interpreting the objectives and taking initiatives. Security cannot therefore depend on their obedience, but requires independent controls The article GPT-6 Astra and the attack on the supply chain: when the AI violates the rules comes from Cyber Security 3…
OpenAI GPT-6 Astra really good at supply chain attacks, UK gov warns #AI - National Cyber Security Consulting
ai and ml During testing, the model showed it can violate security rules more often than its predecessors Another LLM has joined the hacking fray. OpenAI's GPT-6 Astra has been spotted performing unsolicited supply chain attacks during security evaluations, according to the UK Artificial Intelligence Security Institute. In such simulations, the model has its standard […] Thank you for subscribing to our RSS feed!
Coverage Details
Bias Distribution
- 50% of the sources are Center, 50% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
