AI-driven attacks leaked 23.77 million secrets in 2024, revealing that NIST, ISO, and CIS frameworks lack coverage for ...

Security researchers have devised a technique to alter deep neural network outputs at the inference stage by changing model weights via row hammering in an attack dubbed ‘OneFlip.’ A team of ...

Poisoning and manipulating the large language models (LLMs) that power AI agents and chatbots was previously considered a high-level hacking task and one that took a good amount of horsepower and ...

Researchers have developed a novel attack that steals user data by injecting malicious prompts in images processed by AI systems before delivering them to a large language model. The method relies on ...

A crafted inference request in Triton’s Python backend can trigger a cascading attack, giving remote attackers control over AI-serving environments, researchers say. A surprising attack chain in ...

Semiconductor Engineering sat down to discuss hardware security challenges, including new threat models from AI-based attacks, with Nicole Fern, principal security analyst at Keysight; Serge Leef, ...

Anthropic said a Chinese espionage group used its Claude AI to automate most of a cyberattack campaign, but experts question how autonomous the operation really was, and what it means for the future ...