LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities

Documenti analoghi

• Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models
  di: Nakka, Kalyan, et al.
  Pubblicazione: (2024)
• A Machine Learning-Based Framework for Assessing Cryptographic Indistinguishability of Lightweight Block Ciphers
  di: Dani, Jimmy, et al.
  Pubblicazione: (2024)
• BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
  di: Nakka, Kalyan, et al.
  Pubblicazione: (2025)
• When AI Defeats Password Deception! A Deep Learning Framework to Distinguish Passwords and Honeywords
  di: Dani, Jimmy, et al.
  Pubblicazione: (2024)
• The First Early Evidence of the Use of Browser Fingerprinting for Online Tracking
  di: Liu, Zengrui, et al.
  Pubblicazione: (2024)