LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs

Documenti analoghi

• LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
  di: Ibanez-Lissen, Luis, et al.
  Pubblicazione: (2024)
• Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique
  di: Li, Yanming, et al.
  Pubblicazione: (2025)
• DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs
  di: Thompson, Isaiah, et al.
  Pubblicazione: (2026)
• Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs
  di: Ma, Tengyun, et al.
  Pubblicazione: (2025)
• eyeballvul: a future-proof benchmark for vulnerability detection in the wild
  di: Chauvin, Timothee
  Pubblicazione: (2024)