BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models

Ähnliche Einträge

• Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
  von: Wang, Shuqiang, et al.
  Veröffentlicht: (2026)
• From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
  von: Liu, Junhao, et al.
  Veröffentlicht: (2025)
• ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoning
  von: Guan, Shaowei, et al.
  Veröffentlicht: (2025)
• POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
  von: Li, Xinyu, et al.
  Veröffentlicht: (2025)
• Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
  von: Xu, Rongwu, et al.
  Veröffentlicht: (2024)