# The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models

arXiv: https://arxiv.org/abs/2502.01225 · HTML: https://mlsanity.com/paper/2502.01225/

## Key facts

- Cited by 12 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 2 of its 12 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 2 of 2)

- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://mlsanity.com/paper/2407.15549/) (2024)

## Built on by (most cited first, 12 of 12)

- [Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable](https://mlsanity.com/paper/2503.00555/) (2025)
- [SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.08813/) (2025)
- [Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings](https://mlsanity.com/paper/2503.15092/) (2025)
- [Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering](https://mlsanity.com/paper/2504.07137/) (2025)
- [UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases](https://mlsanity.com/paper/2507.21652/) (2025)
- [DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey](https://mlsanity.com/paper/2503.09956/) (2025)
- [When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models](https://mlsanity.com/paper/2510.21285/) (2025)
- [RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs](https://mlsanity.com/paper/2605.02946/) (2026)
- [AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models](https://mlsanity.com/paper/2509.24269/) (2025)
- [Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink](https://mlsanity.com/paper/2602.05228/) (2026)
- [ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection](https://mlsanity.com/paper/2508.11281/) (2025)
- [AI-Generated PowerShell Malware: An Experimental Framework and Dataset](https://mlsanity.com/paper/2606.30819/) (2026)

## Abstract (arXiv)

Large language models are typically trained on vast amounts of data during the pre-training phase, which may include some potentially harmful information. Fine-tuning attacks can exploit this by prompting the model to reveal such behaviours, leading to the generation of harmful content. In this paper, we focus on investigating the performance of the Chain of Thought based reasoning model, DeepSeek, when subjected to fine-tuning attacks. Specifically, we explore how fine-tuning manipulates the model's output, exacerbating the harmfulness of its responses while examining the interaction between the Chain of Thought reasoning and adversarial inputs. Through this study, we aim to shed light on the vulnerability of Chain of Thought enabled models to fine-tuning attacks and the implications for their safety and ethical deployment.