Cisco research finds standard AI safety benchmarks miss the real threat (opens in new tab)

Enterprises deploying closed AI models have generally relied on published safety benchmarks to assess risk before procurement and deployment decisions. New research from Cisco’s AI Threat Intelligence and Security Research team finds those benchmarks may systematically understate the threat. Standard safety tests submit a single adversarial prompt and record the model’s response. Multi-turn attacks work differently. An attacker maintains a conversation across multiple exchanges, iterating and...