Ngā tūemi rite

• Context manipulation attacks : Web agents are susceptible to corrupted memory
  mā: Patlan, Atharv Singh, me ētahi atu.
  I whakaputaina: (2025)
• MURMUR: Using cross-user chatter to break collaborative language agents in groups
  mā: Patlan, Atharv Singh, me ētahi atu.
  I whakaputaina: (2025)
• CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
  mā: Zhu, Yuxuan, me ētahi atu.
  I whakaputaina: (2025)
• Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models
  mā: Del Rosario, Ron F.
  I whakaputaina: (2025)
• Exploiting Web Search Tools of AI Agents for Data Exfiltration
  mā: Rall, Dennis, me ētahi atu.
  I whakaputaina: (2025)