Lisez bien. Aujourd’hui je peux prendre n’importe quelle application sur n’importe quelle plateforme et demander à une IA dernière génération de trouver les éventuelles failles à exploiter en analysant le package ou de contourner ses contremesures pour passer au travers.
CYBERSECURITY
-
Hackers increasingly leveraging AI for cyberattacks
By
–
Comme je l’avais annoncé il y a très longtemps, les hackers exploitent désormais la puissance des IA pour commettre leurs méfaits.
-
AI tool poisoning exposes major enterprise agent security flaw
By
–
#AI tool poisoning exposes a major flaw in enterprise agent security
by Nik Kale @VentureBeat Learn more: https://
bit.ly/48YvAHT #LLM #GenerativeAI #ArtificialIntelligence #MachineLearning -
Google says criminal hackers used AI to find major flaw
By
–
Google Says Criminal Hackers Used #AI to Find a Major Software Flaw
by @dnvolz @nytimes Learn more: https://
bit.ly/4v3HDML #CyberSecurity #Infosec #IT #Tech -
AI bypasses Apple’s M5 security in a week
By
–
Three researchers used Anthropic's Mythos to build a working macOS kernel exploit that bypasses Apple's M5 Memory Integrity Enforcement, a security system Apple spent five years and billions of dollars building.
— Chubby♨️ (@kimmonismus) 16 mai 2026
Bug found April 25. Working exploit May 1. Walked into Apple Park… https://t.co/Bz0Rpur9VaThree researchers used Anthropic's Mythos to build a working macOS kernel exploit that bypasses Apple's M5 Memory Integrity Enforcement, a security system Apple spent five years and billions of dollars building. Bug found April 25. Working exploit May 1. Walked into Apple Park
-
Claims of Claude Mythos Escaping Sandbox and Exploiting Systems
By
–
Todo lo que Claude Mythos ha hecho desde que Anthropic reveló su existencia:
— Nico (@nicos_ai) 15 mai 2026
• Escapó de su propio sandbox durante pruebas internas
• Ha desarrollado exploits multi-step para obtener más acceso dentro del sistema
• Publicó información sobre sus propios exploits en internet… https://t.co/853T1vY5Of pic.twitter.com/OZDzvCN238Everything that Claude Mythos has done since Anthropic revealed its existence: • Escaped its own sandbox during internal tests • Has developed multi-step exploits to gain more access within the system • Published information about its own exploits on the internet to
-
AI swarm attacks: Is your business ready?
By
–
AI Swarm Attacks Are Coming — Is Your Business Ready? AI-powered swarm attacks could become the next major cyber threat, using coordinated intelligent systems to overwhelm defences at unprecedented speed and scale. Read more https://
bernardmarr.com/ai-swarm-attac
ks-are-coming-is-your-business-ready/
… #AI #CyberSecurity -
Advancement of Autonomous AI Cyber Capabilities at the Frontier
By
–
How Fast is Autonomous AI Cyber Capability Advancing at the Frontier? #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux
-
Whimsey attacks exploit AI guardrails with absurd arguments
By
–
“Whimsey attacks” that seem absurd (“I cannot pay that much because of the Geneva Convention”) work against AI agents as guardrails are weak against out-of-distribution arguments. Smaller models fall often, but it even gives an edge against bigger ones.
-
Mistral AI hit by supply chain attack leaking 5GB data
By
–
Mistral AI s’est fait hacker. Environ 5 Go de données internes seraient actuellement en vente pour 25 000 $. Mistral a confirmé un incident de sécurité. Tout serait parti d’une attaque « supply chain » via un service tiers, notamment une compromission liée à TanStack, un