When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Documenti analoghi

• Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
  di: Zhang, Boxuan, et al.
  Pubblicazione: (2025)
• When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems
  di: Ren, Qibing, et al.
  Pubblicazione: (2025)
• INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
  di: Zhou, Yijin, et al.
  Pubblicazione: (2026)
• Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning
  di: Yao, Junchi, et al.
  Pubblicazione: (2025)
• MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
  di: Zhang, Ming, et al.
  Pubblicazione: (2025)