Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability

Documenti analoghi

• Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
  di: Hu, Chengyin, et al.
  Pubblicazione: (2026)
• XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs
  di: Hu, Chengyin, et al.
  Pubblicazione: (2026)
• Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems
  di: Hu, Chengyin, et al.
  Pubblicazione: (2026)
• From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
  di: Han, Jiaju, et al.
  Pubblicazione: (2026)
• CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models
  di: Chen, Xiang, et al.
  Pubblicazione: (2026)