GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models

Documenti analoghi

• Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
  di: Das, Badhan Chandra, et al.
  Pubblicazione: (2026)
• QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning
  di: Mia, Md Jueal, et al.
  Pubblicazione: (2024)
• FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model
  di: Mia, Md Jueal, et al.
  Pubblicazione: (2025)
• System Prompt Extraction Attacks and Defenses in Large Language Models
  di: Das, Badhan Chandra, et al.
  Pubblicazione: (2025)
• Security and Privacy Challenges of Large Language Models: A Survey
  di: Das, Badhan Chandra, et al.
  Pubblicazione: (2024)