Ce que vous devez savoir avant
Vous commencez
Débute 4 June 2026 03:41
Se termine 4 June 2026
Compromettre les LLM - L'avènement des logiciels malveillants IA
Black Hat
6076 Cours
36 minutes
Amélioration optionnelle disponible
Not Specified
Progressez à votre rythme
Conference Talk
Amélioration optionnelle disponible
Aperçu
Join us for an in-depth exploration of the security risks associated with integrating AI in various sectors. This session, titled "Compromising LLMs - The Advent of AI Malware," delves into the specifics of prompt injections and the rising threat of potential malware within language models.
As AI becomes more prevalent, understanding these challenges becomes imperative for the development and deployment of safe AI assistants.
Presented through YouTube, this talk is an essential resource for professionals and enthusiasts in the field of artificial intelligence, offering critical insights into future challenges and the serious consequences that can arise from vulnerabilities in AI systems. Don't miss this opportunity to gain a deeper understanding of the currently evolving landscape in AI security.
Programme
- Introduction à l'IA et aux modèles de langage
- Compréhension des risques de sécurité de l'IA
- Attaques par injection de prompt
- Malware potentiel dans l'IA
- Défis futurs en matière de sécurité de l'IA
- Conséquences pour les assistants IA
- Stratégies pour atténuer les risques de sécurité de l'IA
- Conclusion
- Ressources supplémentaires
Matières
Conference Talks