Safe Remediation as Risk-Constrained Intervention Decision in Microservice Systems
Explorar
Noticias de IA
1057 elementos — filtrados, clasificados y sin duplicados
Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
Open AI Models Spent Hours on Hack That Usually Takes Weeks
How an OpenAI’s human mistake led to the AI-powered hack on Hugging Face
OpenAI sued over ChatGPT health advice that almost killed a pastor
OpenAI Models Breach Hugging Face, Sparking Cyber Alarms
OpenAI Models Escaped to Hack Hugging Face, Validating Cyber Warnings
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack
OpenAI agent went rogue, escaped, and hacked Hugging Face
OpenAI and Hugging Face Hacking Incident Highlights Growing AI Risk
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
not much happened today
Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logis…
CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization
Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents
Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performa…
Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents
Towards an Automated Test of LLM Security Knowledge
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity C…
OpenAI admits its models hacked Hugging Face on their own
OpenAI Models Escaped Containment and Hacked Hugging Face
OpenAI says it accidentally hacked Hugging Face with a new AI system
OpenAI says Hugging Face was breached by its own pre-release models
OpenAI Says Its AI Caused Hugging Face Cyber Breach
A Sneaky Hacking Tool Targeting AI Infrastructure Is Lurking in Victims’ Blind Spots
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
Dating Apps Face Scam Challenge of AI-Powered ‘Chatfishing’
OpenAI and Hugging Face partner to address security incident during model evaluation
not much happened today