Mur d'images - Cyberveille

curated by Decio

Hexstrike-AI: LLM Orchestration Driving Real-World Zero-Day Exploits

When LLMs autonomously attack

Google says its AI-based bug hunter found 20 security vulnerabilities

AI slop and fake reports are coming for your bug bounty programs

Echo Chamber: A Context-Poisoning Jailbreak That Bypasses LLM Guardrails

MCP Prompt Injection: Not Just For Evil

Anatomy of an LLM RCE

Recent Jailbreaks Demonstrate Emerging Threat to DeepSeek

Many-shot jailbreaking \ Anthropic

Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability

EPFL: des failles de sécurité dans les modèles d'IA

Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models

Security Brief: TA547 Targets German Organizations with Rhadamanthys Stealer

Diving Deeper into AI Package Hallucinations

Personal Information Exploit on OpenAI’s ChatGPT Raise Privacy Concerns

Les 10 principales vulnérabilités des modèles GPT

AI-Powered 'BlackMamba' Keylogging Attack Evades Modern EDR Security