Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks

Documenti analoghi

• Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
  di: Ma, Jiachen, et al.
  Pubblicazione: (2024)
• DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
  di: Ou, Haoran, et al.
  Pubblicazione: (2026)
• Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks
  di: Sahu, Anubhab, et al.
  Pubblicazione: (2026)
• A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing
  di: Gibert, Daniel, et al.
  Pubblicazione: (2024)
• SoK: Robustness in Large Language Models against Jailbreak Attacks
  di: Xu, Feiyue, et al.
  Pubblicazione: (2026)