Leading AI models are more vulnerable to malicious prompts than vendors claim
Source: Cybersecuritydive
Published:
<p>Hackers could subvert frontier models with attacks that their developers overlook, Cisco said.</p> <p>Cisco’s evaluation of 15 leading AI models from OpenAI, Anthropic, Google, Amazon and xAI “found that single-turn attack success rate (ASR) is not a reliable proxy for what happens when an attack