SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats

Documenti analoghi

• SoK: Unlearnability and Unlearning for Model Dememorization
  di: Zhang, Mengying, et al.
  Pubblicazione: (2026)
• SoK: Practical Aspects of Releasing Differentially Private Graphs
  di: D'Silva, Nicholas, et al.
  Pubblicazione: (2026)
• What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift
  di: Chang, Jiamin, et al.
  Pubblicazione: (2025)
• SoK: Can Trajectory Generation Combine Privacy and Utility?
  di: Buchholz, Erik, et al.
  Pubblicazione: (2024)
• If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems
  di: Chang, Jiamin, et al.
  Pubblicazione: (2026)