ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models

Documenti analoghi

• LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection
  di: Piehl, Mitchell, et al.
  Pubblicazione: (2026)
• Robustifying Safety-Aligned Large Language Models through Clean Data Curation
  di: Liu, Xiaoqun, et al.
  Pubblicazione: (2024)
• MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
  di: Ha, Hyeonjeong, et al.
  Pubblicazione: (2026)
• Memory-Augmented Architecture for Long-Term Context Handling in Large Language Models
  di: Shinwari, Haseeb Ullah Khan, et al.
  Pubblicazione: (2025)
• VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models
  di: Ye, Muchao, et al.
  Pubblicazione: (2024)