# ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models

arXiv: https://arxiv.org/abs/2602.00154 · HTML: https://mlsanity.com/paper/2602.00154/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Sponge Examples: Energy-Latency Attacks on Neural Networks](https://mlsanity.com/paper/2006.03463/) (2020)
- [OverThink: Slowdown Attacks on Reasoning LLMs](https://mlsanity.com/paper/2502.02542/) (2025)
- [Coercing LLMs to do and reveal (almost) anything](https://mlsanity.com/paper/2402.14020/) (2024)
- [Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images](https://mlsanity.com/paper/2401.11170/) (2024)
- [Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States](https://mlsanity.com/paper/2402.09733/) (2024)
- [Denial-of-Service Poisoning Attacks against Large Language Models](https://mlsanity.com/paper/2410.10760/) (2024)
- [Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings](https://mlsanity.com/paper/2412.13879/) (2024)
- [An Engorgio Prompt Makes Large Language Model Babble on](https://mlsanity.com/paper/2412.19394/) (2024)
- [Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors](https://mlsanity.com/paper/2205.13618/) (2022)
- [Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models](https://mlsanity.com/paper/2503.01781/) (2025)
- [ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking](https://mlsanity.com/paper/2512.07086/) (2025)
- [Excessive Reasoning Attack on Reasoning LLMs](https://mlsanity.com/paper/2506.14374/) (2025)
- [POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization](https://mlsanity.com/paper/2508.19277/) (2025)
- [LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops](https://mlsanity.com/paper/2506.14493/) (2025)
- [The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision](https://mlsanity.com/paper/2403.18587/) (2024)

## Built on by (most cited first, 5 of 5)

- [Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2603.25412/) (2026)
- [From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails](https://mlsanity.com/paper/2606.14517/) (2026)
- [ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving](https://mlsanity.com/paper/2605.29114/) (2026)
- [RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks](https://mlsanity.com/paper/2606.07968/) (2026)
- [SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance](https://mlsanity.com/paper/2608.18921/) (2026)

## Abstract (arXiv)

Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time denial-of-service (PI-DoS) attacks that exploit the high computational cost of reasoning. We first formalize inference cost for LRMs and define PI-DoS, then prove that any practical PI-DoS attack should satisfy three properties: (1) a high amplification ratio, where each query induces a disproportionately long reasoning trace relative to its own length; (ii) stealthiness, in which prompts and responses remain on the natural language manifold and evade distribution shift detectors; and (iii) optimizability, in which the attack supports efficient optimization without being slowed by its own success. Under this framework, we present ReasoningBomb, a reinforcement-learning-based PI-DoS framework that is guided by a constant-time surrogate reward and trains a large reasoning-model attacker to generate short natural prompts that drive victim LRMs into pathologically long and often effectively non-terminating reasoning. Across seven open-source models (including LLMs and LRMs) and three commercial LRMs, ReasoningBomb induces 18,759 completion tokens on average and 19,263 reasoning tokens on average across reasoning models. It outperforms the the runner-up baseline by 35% in completion tokens and 38% in reasoning tokens, while inducing 6-7x more tokens than benign queries and achieving 286.7x input-to-output amplification ratio averaged across all samples. Additionally, our method achieves 99.8% bypass rate on input-based detection, 98.7% on output-based detection, and 98.4% against strict dual-stage joint detection.