Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment

Documenti analoghi

• Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments
  di: Zheng, Xinyi, et al.
  Pubblicazione: (2024)
• Towards Context-aware Mobile Privacy Notice: Implementation of A Deployable Contextual Privacy Policies Generator
  di: Gong, Haochen, et al.
  Pubblicazione: (2025)
• Safety Interventions against Adversarial Patches in an Open-Source Driver Assistance System
  di: Chen, Cheng, et al.
  Pubblicazione: (2025)
• Demonstration Attack against In-Context Learning for Code Intelligence
  di: Ge, Yifei, et al.
  Pubblicazione: (2024)
• DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems
  di: Yang, Rui, et al.
  Pubblicazione: (2025)