$\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models

Ähnliche Einträge

• DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Demonstration and Reasoning
  von: Qiu, Hongye, et al.
  Veröffentlicht: (2025)
• Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks
  von: Mu, Lin, et al.
  Veröffentlicht: (2025)
• DROJ: A Prompt-Driven Attack against Large Language Models
  von: Hu, Leyang, et al.
  Veröffentlicht: (2024)
• Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
  von: Zhao, Shuai, et al.
  Veröffentlicht: (2023)
• Robust Prompt Optimization for Large Language Models Against Distribution Shifts
  von: Li, Moxin, et al.
  Veröffentlicht: (2023)