Hoax: Fake Russian “troll” error message
Explorar
Noticias de IA
1359 elementos — filtrados, clasificados y sin duplicados
CyberAv3ngers: Iran-linked cyber research activity
STORM-0817: Iran-linked malware and scraping activity
Tort Report: Abusive reporting activity
Rwandan election content: Political commenting network
Bet Bot: Gambling spam network
SweetSpecter: China-linked cyber activity
Hugging Face partners with TruffleHog to Scan for Secrets
2024 Security Feature Highlights
Empowering defenders through our Cybersecurity Grant Program
Disrupting deceptive uses of AI by covert influence operations
CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabil…
OpenAI safety practices
Understanding the source of what we see and hear online
Operation "Doppelganger": Russian influence activity targeting Ukraine
IUVM: Iran-linked influence content network
Operation "Zero Zeno": Israel-linked influence activity
Operation "Spamouflage": China-linked influence activity
"Bad Grammar": Russian-linked Telegram comment activity
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Hugging Face partners with Wiz Research to Improve AI Security
Introducing the Red-Teaming Resistance Leaderboard
Disrupting malicious uses of AI by state-affiliated threat actors
Building an early warning system for LLM-aided biological threat creation
An Introduction to AI Secure LLM Safety Leaderboard
Nightshade poisons AI art... kinda?
Amazon’s Q has ‘severe hallucinations’ and leaks confidential data in public preview, emp…
Frontier risk and preparedness
OpenAI Red Teaming Network
Announcing OpenAI’s Bug Bounty Program