Researchers Find Easy Way to Jailbreak Every Major AI, From ChatGPT to Claude

Researchers Find Easy Way to Jailbreak Every Major AI, From ChatGPT to Claude

Security researchers have discovered a highly effective new jailbreak that can dupe nearly every major large language model into producing harmful output, from explaining how to build nuclear weapons to encouraging self-harm. As detailed in a writeup by the team at AI security firm HiddenLayer, the exploit is a prompt injection technique that can bypass the "safety guardrails across all major frontier AI models," including Google's Gemini 2.5, A…

Two Systemic Jailbreaks Uncovered, Exposing Widespread Vulnerabilities in Generative AI Models

Two significant security vulnerabilities in generative AI systems have been discovered, allowing attackers to bypass safety protocols and extract potentially dangerous content from multiple popular AI platforms. These “jailbreaks” affect services from industry leaders including OpenAI, Google, Microsoft, and Anthropic,… Read more → The post Two Systemic Jailbreaks Uncovered, Exposing Widespread Vulnerabilities in Generative AI Models appeared fi…

New Trick Breaks AI Safeguards—ChatGPT, Claude, Gemini All Vulnerable

Experts Discover Vulnerability in AI Chatbots Like ChatGPT & ClaudeSecurity researchers have discovered a new jailbreak technique that can bypass safety guardrails across major AI models, including ChatGPT, Claude, and Gemini. The exploit, developed by AI security firm HiddenLayer, uses a combination of policy file formatting, roleplaying, and leetspeak to trick AI into generating harmful content. Jailbreaking, in the context of AI, refers to te…

HiddenLayer Researchers Surface Prompt Technique Bypassing All AI Guardrails

HiddenLayer has disclosed its researchers discovered a prompt injection technique that bypasses instruction hierarchy and safety guardrails.