Explorar

Noticias de IA

1057 elementos — filtrados, clasificados y sin duplicados

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