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

Documenti analoghi

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