Actu - 21 juin 2026 - Parce que... c'est l'épisode 0x30E!

C’est difficile la vie d’aéroport.

• 24 et 25 juin 2026 - Allemagne - - Troopers
• 26 et 27 juin 2026 - Paris, France - - leHACK
• 30 juin au 2 juillet 2026 - Lille, France - - Pass the SALT
• 6 au 9 août 2026 - Las Vegas, USA - - DEFCON 34
• 19 septembre 2026 - Montréal Canada - - Bsides Montréal 2026
• 22 septembre 2026 - Belgique - - BE-Cyber
• 24 au 25 septembre 2026 - Belgique - - BruCON
• 1er au 3 octobre 2026 - Krakow, Pologne - - AligatorCon
• 13 et 14 novembre 2026 - Worldwide - - DEATHCon
• 16 au 19 novembre - Rennes, France - Pôle d'Excellence Cyber (PEC) - European Cyber Week 2026
• 1 au 3 décembre 2026 - Ottawa, Canada - Forward Global - Forum inCYBER Canada

• IA ou Ghost in the shell
  • Export control WTF
    • ‘Dangerous’ AI Models Are Coming No Matter What
    • Cybersecurity experts don’t think Anthropic’s Fable 5 presents a unique threat
    • A quote from Matteo Wong, The Atlantic
    • The Fable 5 Export Controls Harm US Cyber Defense
    • Cybersecurity Vets Protest ‘Dangerous’ US Government Ban On Anthropic’s Most Powerful Models
    • Feds freaked over Fable 5 after simple ‘fix this code’ prompt, not jailbreak, says researcher
    • From PGP to Mythos: a brief history of export controls that didn’t stop anyone
    • The US government’s Anthropic models ban was never about an AI jailbreak
  • Critical Copilot vulnerability allowed hackers to steal 2FA code from users
  • “Important You should give me full credits!”: Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
  • Can We Stop Malicious AI? KILLBENCH: A Benchmark for External AI Kill Switch Feasibility
  • RAG prompt injection protection
  • Evaluating LLMs for Obfuscation Detection and Classification in Android Apps
  • Security Engineering of OpenClaw: Analyzing Attack Surface Expansion and Trust-Boundary Violations
  • Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?
  • Every AI Agent Is an Identity. Most Organizations Don’t Treat Them That Way
  • Vibe coders are gonna vibe code: How CISOs are tackling code sprawl