Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment

Documenti analoghi

• Exploiting Cross-Layer Vulnerabilities: Off-Path Attacks on the TCP/IP Protocol Suite
  di: Feng, Xuewei, et al.
  Pubblicazione: (2024)
• DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
  di: Zhang, Yitong, et al.
  Pubblicazione: (2025)
• LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
  di: Zhang, Yuanhe, et al.
  Pubblicazione: (2025)
• When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
  di: Li, Junchen, et al.
  Pubblicazione: (2026)
• DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization
  di: Tang, Wenxin, et al.
  Pubblicazione: (2026)