Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications

Documenti analoghi

• HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing
  di: Muzsai, Lajos, et al.
  Pubblicazione: (2024)
• Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks
  di: Paim, Kayua Oleques, et al.
  Pubblicazione: (2025)
• Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges
  di: Muzsai, Lajos, et al.
  Pubblicazione: (2025)
• Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
  di: Schaeffer, Joachim, et al.
  Pubblicazione: (2026)
• Toward Autonomous and Efficient Cybersecurity: A Multi-Objective AutoML-based Intrusion Detection System
  di: Yang, Li, et al.
  Pubblicazione: (2025)