Researchers broke every AI defense they tested. Here are 7 questions to ask vendors. | VentureBeat

Researchers from OpenAI, Anthropic, and Google DeepMind found that adaptive attacks bypassed 12 AI defenses that claimed near-zero risk. The research showed that most AI security products are being tested against attackers that don’t behave like real attackers. The research team tested prompting-based, training-based, and filtering-based defenses under adaptive attack conditions. All collapsed. The researchers designed a rigorous methodology to stress-test those claims. Their approach included 14 authors and a $20,000 prize pool for successful attacks. The research points to specific architectural requirements. Security leaders need answers to these questions before any procurement conversation starts, as each one maps directly to a failure documented in the research.