New AI Jailbreak Method ‘Bad Likert Judge’ Boosts Attack Success Rates by Over 60%

Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model’s (LLM) safety guardrails and produce potentially harmful or malicious responses.
The multi-turn (aka many-shot) attack strateg… Continue reading New AI Jailbreak Method ‘Bad Likert Judge’ Boosts Attack Success Rates by Over 60%

Posted in Uncategorized

NPM Package Disguised as an Ethereum Tool Deploys Quasar RAT

Researchers discovered a malicious package on the npm package registry that resembles a library for Ethereum smart contract vulnerabilities but actually drops an open-source remote access trojan called Quasar RAT onto developer systems. Continue reading NPM Package Disguised as an Ethereum Tool Deploys Quasar RAT