OverThink: Slowdown Attacks on Reasoning LLMs

Understand

Most flagship language models generate explicit reasoning chains, enabling inference-time scaling.

• However, producing these reasoning chains increases token usage (i.e., reasoning tokens), which in turn increases latency and costs.
• Our OverThink attack increases overhead for applications that rely on reasoning language models (RLMs) and external context by forcing them to spend substantially more reasoning tokens while still producing contextually correct answers.
• An adversary mounts an attack by injecting decoy reasoning problems into public content that is consumed by RLM at inference time.