VAULT: Vigilant Adversarial Updates via LLM-Driven Retrieval-Augmented Generation for NLI

Documenti analoghi

• Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
  di: Kazoom, Roie, et al.
  Pubblicazione: (2025)
• LISAA: A Framework for Large Language Model Information Security Awareness Assessment
  di: Cohen, Ofir, et al.
  Pubblicazione: (2024)
• Boundary on the Table: Efficient Black-Box Decision-Based Attacks for Structured Data
  di: Kazoom, Roie, et al.
  Pubblicazione: (2025)
• Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GAN
  di: Kazoom, Roie, et al.
  Pubblicazione: (2025)
• Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks
  di: Kazoom, Roie, et al.
  Pubblicazione: (2024)