BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Documenti analoghi

• CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
  di: Li, Yuetai, et al.
  Pubblicazione: (2024)
• CBD: A Certified Backdoor Detector Based on Local Dominant Probability
  di: Xiang, Zhen, et al.
  Pubblicazione: (2023)
• Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
  di: Sahabandu, Dinuka, et al.
  Pubblicazione: (2024)
• SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
  di: Jiang, Fengqing, et al.
  Pubblicazione: (2025)
• ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
  di: Xu, Zhangchen, et al.
  Pubblicazione: (2024)