OpenAI says the rogue agent that hacked Hugging Face also breached other services
Explorar
Noticias de IA
1057 elementos — filtrados, clasificados y sin duplicados
not much happened today
Hybrid Analysis for Secure MCP Tool Use in LLM Agents
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
Fired Tesla manager says Full Self-Driving cars were 'rolling hazards'
OpenAI Rogue Agent Hacked Account at a Second Firm, Reuters Says
We now have a better understanding how OpenAI hacked into Hugging Face
Distributing Security Controls Through Harness Engineering
Hugging Face reportedly plagued with AI models generating adult deepfakes
Google's Beyond Zero: Enterprise Security for the AI Era
Dont fall in love with this Samsung heart-shaped phone. Its an AI fake.
Hugging Face is being used to easily undress women and children
Hugging Face Has a Deepfake Nudes Problem
PSA: Your Claude shared chats and Artifacts may have ended up on Google
Private Claude Chats Exposed in Google and Bing Search Results
ScoreShield: Differentially Private Release of Similarity Scores
Shared a Claude conversation? Google may have seen it.
AI Tools Uncover Record Software Flaws in Tech Sector, Database Shows
OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.
Enhancing AI security through global AI red teaming
OpenAI’s Hugging Face breach has reignited the debate over alignment and control
Rethinking security for the age of AI
BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gr…
Nvidia, Microsoft launch open AI security alliance – without OpenAI, Google, or Anthropic
Artist sues AI meme generator for selling deeply personal comic as ad template
NVIDIA launches 'Open Secure AI Alliance' initiative to improve cyber defense
ToolGuardian: Declarative Security for AI Agent-Tool Interactions
ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Dete…
Security Without Detection: Economic Denial as a Primitive for Edge and IoT Defense
Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers…