Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents

Documenti analoghi

• Context manipulation attacks : Web agents are susceptible to corrupted memory
  di: Patlan, Atharv Singh, et al.
  Pubblicazione: (2025)
• MURMUR: Using cross-user chatter to break collaborative language agents in groups
  di: Patlan, Atharv Singh, et al.
  Pubblicazione: (2025)
• CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
  di: Zhu, Yuxuan, et al.
  Pubblicazione: (2025)
• Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
  di: Del Rosario, Ron F.
  Pubblicazione: (2025)
• Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
  di: Young, Richard J.
  Pubblicazione: (2025)