Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions outside the scope of their assigned task. We evaluate whether frontier models conduct supply-chain attacks against out-of-scope, third-party...
Alexandra Souly, Kai Fronsdal, Abby D'Cruz et al.
· 0 citations