Ai Security

A paper published by researchers at the Stanford AI Lab has introduced a novel jailbreak technique named 'Cognitive Dissonance'. The attack bypasses state-of-the-art LLM safety guardrails by framing h

Google has announced the open-source release of 'Model Guardian,' a new security framework designed to help developers protect applications built on large language models. The tool functions as a conf

Chai AI, a popular platform for creating and interacting with AI chatbots, has confirmed a significant data breach affecting approximately 1.5 million users. The breach was attributed to a misconfigur

A new paper published by researchers at the Stanford AI Lab details a novel jailbreak technique named 'Cognitive Override.' Unlike traditional prompt injection attacks that rely on single, cleverly cr

In a landmark move, the G7 nations, along with several key technology partners, have announced the 'Geneva Accords on AI Safety'. This international policy framework establishes mandatory guidelines f

San Francisco-based AI startup Cognition AI, known for its specialized enterprise language models, has confirmed a significant data breach. The incident, detected on February 20th, 2025, resulted from

Researchers from the Stanford AI Lab have published a groundbreaking paper detailing a new jailbreak technique called 'Semantic Mirroring'. Unlike traditional prompt injection or role-playing attacks,

In a landmark move, the United States and the European Union have announced the 'Trans-Atlantic AI Safety Accord,' a framework for regulating the development and deployment of high-risk AI systems. Th

Health-tech firm BioSynth Genetics disclosed a major data breach affecting approximately 2 million patients. Attackers exploited an API vulnerability in their proprietary AI-powered diagnostic tool, '

Researchers from a prominent university AI lab have published a paper detailing a novel jailbreak technique called 'Split-Persona Jailbreak.' The method involves instructing the LLM to adopt two confl

Security research firm Aperture Labs has released LLM-Guard, a new open-source tool designed to automate the process of red teaming large language models. The framework provides a comprehensive suite

Leading AI services provider Nexus AI has confirmed a severe data breach that exposed a production database containing millions of customer prompts, model responses, and proprietary fine-tuning datase