Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities

Documenti analoghi

• Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
  di: Miao, Ziqi, et al.
  Pubblicazione: (2025)
• Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
  di: Qu, Jingen, et al.
  Pubblicazione: (2025)
• Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
  di: Ding, Yi, et al.
  Pubblicazione: (2025)
• VLSBench: Unveiling Visual Leakage in Multimodal Safety
  di: Hu, Xuhao, et al.
  Pubblicazione: (2024)
• GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
  di: Li, Xueyi, et al.
  Pubblicazione: (2026)