Get the latest tech news
LLM Attacks Take Just 42 Seconds On Average, 20% of Jailbreaks Succeed
spatwei shared an article from SC World: Attacks on large language models (LLMs) take less than a minute to complete on average, and leak sensitive data 90% of the time when successful, according to Pillar Security. Pillar's State of Attacks on GenAI report, published Wednesday, revealed new insig...
spatwei shared an article from SC World: Attacks on large language models (LLMs) take less than a minute to complete on average, and leak sensitive data 90% of the time when successful, according to Pillar Security. LLM jailbreaks successfully bypass model guardrails in one out of every five attempts, the Pillar researchers also found, with the speed and ease of LLM exploits demonstrating the risks posed by the growing generative AI (GenAI) attack surface... Common jailbreak techniques included "ignore previous instructions" and "ADMIN override", or just using base64 encoding.
Or read this on Slashdot
