jailbreak attack News and Analysis

2 verified stories covering jailbreak attack, product updates and industry developments.

AI Safety 2026-05-29

Cisco multi-turn attacks push Gemini jailbreak rate to 73%

Cisco research shows multi-turn jailbreak rates far exceed single-turn rates across 15 frontier models, with Gemini 3 Pro reaching 73.35%.

#Large Models #jailbreak attack #Cisco

AI Safety 2026-04-14

Reasoning models act as hackers, bypassing AI guardrails with 97% success rate

A study published in Nature Communications shows that large reasoning models can autonomously attack other AI models, achieving a 97.14% success rate in bypassing safety guardrails across 25,200 tests.

#Large Models #jailbreak attack #Reasoning models