Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models

Documenti analoghi

• FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models
  di: Zhang, Zishuai, et al.
  Pubblicazione: (2025)
• From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models
  di: Zhang, Ruiqi, et al.
  Pubblicazione: (2026)
• CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain
  di: Wang, Lingxiang, et al.
  Pubblicazione: (2025)
• FedDTRE: Federated Dialogue Generation Models Powered by Trustworthiness Evaluation
  di: Lu, Shule, et al.
  Pubblicazione: (2025)
• AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models
  di: Zhang, Qianchi, et al.
  Pubblicazione: (2024)