# Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models

arXiv: https://arxiv.org/abs/2601.10294 · HTML: https://mlsanity.com/paper/2601.10294/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking](https://mlsanity.com/paper/2502.12893/) (2025)
- [Attention Tracker: Detecting Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2411.00348/) (2024)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [Challenges for Toxic Comment Classification: An In-Depth Error Analysis](https://mlsanity.com/paper/1809.07572/) (2018)
- [A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos](https://mlsanity.com/paper/2502.15806/) (2025)
- [Defending Against Prompt Injection With a Few DefensiveTokens](https://mlsanity.com/paper/2507.07974/) (2025)
- [Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?](https://mlsanity.com/paper/2002.09919/) (2020)
- [ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs](https://mlsanity.com/paper/2504.05605/) (2025)
- [TopicAttack: An Indirect Prompt Injection Attack via Topic Transition](https://mlsanity.com/paper/2507.13686/) (2025)
- [Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization](https://mlsanity.com/paper/2405.14189/) (2024)
- [Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree](https://mlsanity.com/paper/2507.14799/) (2025)
- [Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2512.08417/) (2025)
- [Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior](https://mlsanity.com/paper/2508.19287/) (2025)
- [Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators](https://mlsanity.com/paper/2504.05689/) (2025)

## Built on by (most cited first, 1 of 1)

- [ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments](https://mlsanity.com/paper/2607.24964/) (2026)

## Abstract (arXiv)

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this perspective is incomplete and highlight a critical vulnerability in Reasoning Alignment. We expose the inherent fragility of current alignment techniques by proposing a new adversarial prompt attack paradigm: Reasoning Hijacking. To demonstrate this vulnerability, we instantiate it via the Criteria Attack, which subverts model judgments by injecting spurious decision criteria without altering the high-level task goal. Unlike Goal Hijacking, which attempts to override the system prompt, Reasoning Hijacking keeps the task goal intact but manipulates the model's decision-making logic by injecting spurious reasoning shortcuts. Through extensive experiments on three different tasks (toxic comment, negative review, and spam detection), we demonstrate that even state-of-the-art models are highly fragile, consistently prioritizing injected heuristic shortcuts over rigorous semantic analysis. Crucially, because the model's explicit intent remains aligned with the user's instructions, these attacks can bypass defenses designed to detect goal deviation (e.g., SecAlign, StruQ), revealing a fundamental blind spot in the current safety landscape. Data and code are available at https://github.com/Yuan-Hou/criteria_attack.