UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Documenti analoghi

• On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks
  di: Bi, Ting, et al.
  Pubblicazione: (2025)
• REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations
  di: Yu, Tianlong, et al.
  Pubblicazione: (2025)
• SEAR: A Multimodal Dataset for Analyzing AR-LLM-Driven Social Engineering Behaviors
  di: Yu, Tianlong, et al.
  Pubblicazione: (2025)
• PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks
  di: Yu, Tianlong, et al.
  Pubblicazione: (2026)
• Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
  di: Li, Yuying, et al.
  Pubblicazione: (2024)