Cyberveilleby Decio
Nuage de tags
Mur d'images
Quotidien
Flux RSS
  • Flux RSS
  • Daily Feed
  • Weekly Feed
  • Monthly Feed
Filtres

Liens par page

  • 20 links
  • 50 links
  • 100 links

Filtres

Untagged links
3 résultats taggé LLM  ✕
Les 10 principales vulnérabilités des modèles GPT https://www.ictjournal.ch/articles/2023-11-17/les-10-principales-vulnerabilites-des-modeles-gpt
17/11/2023 21:08:44
QRCode
archive.org
thumbnail

Les grands modèles de langage peuvent être sujets à des cyberattaques et mettre en danger la sécurité des systèmes

ictjournal FR chatGPT cyberattaques vulnérabilités LLM OWASP top10
Large Language Models and Elections https://www.schneier.com/blog/archives/2023/05/large-language-models-and-elections.html
04/05/2023 16:16:24
QRCode
archive.org

Earlier this week, the Republican National Committee released a video that it claims was “built entirely with AI imagery.” The content of the ad isn’t especially novel—a dystopian vision of America under a second term with President Joe Biden—but the deliberate emphasis on the technology used to create it stands out: It’s a “Daisy” moment for the 2020s.

Schneier EN 2023 LLM election disinformation AI
AI-Powered 'BlackMamba' Keylogging Attack Evades Modern EDR Security https://www.darkreading.com/endpoint/ai-blackmamba-keylogging-edr-security
03/05/2023 09:43:06
QRCode
archive.org
thumbnail

Researchers warn that polymorphic malware created with ChatGPT and other LLMs will force a reinvention of security automation.

darkreading EN 2023 ChatGPT EDR evasion Polymorphic BlackMamba LLM
2001 links
Shaarli - Le gestionnaire de marque-pages personnel, minimaliste, et sans base de données par la communauté Shaarli - Theme by kalvn - Curated by Decio