# Detecting Adversarial Fine-tuning with Auditing Agents

arXiv: https://arxiv.org/abs/2510.16255 · HTML: https://mlsanity.com/paper/2510.16255/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 18 of 18)

- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models](https://mlsanity.com/paper/2310.02949/) (2023)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](https://mlsanity.com/paper/2311.09528/) (2023)
- [Subliminal Learning: Language models transmit behavioral traits via hidden signals in data](https://mlsanity.com/paper/2507.14805/) (2025)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [Persona Features Control Emergent Misalignment](https://mlsanity.com/paper/2506.19823/) (2025)
- [Auditing language models for hidden objectives](https://mlsanity.com/paper/2503.10965/) (2025)
- [Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation](https://mlsanity.com/paper/2406.20053/) (2024)
- [Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning](https://mlsanity.com/paper/2507.16795/) (2025)
- [Safety-Aware Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2410.10014/) (2024)
- [Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment](https://mlsanity.com/paper/2402.14968/) (2024)
- [Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety](https://mlsanity.com/paper/2505.06843/) (2025)
- [A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding](https://mlsanity.com/paper/2406.05540/) (2024)
- [Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks](https://mlsanity.com/paper/2508.17158/) (2025)
- [Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs](https://mlsanity.com/paper/2502.14828/) (2025)

## Built on by (most cited first, 3 of 3)

- [Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence](https://mlsanity.com/paper/2603.00498/) (2026)
- [QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals](https://mlsanity.com/paper/2602.02581/) (2026)
- [Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink](https://mlsanity.com/paper/2602.05228/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly concerning, such attacks may avoid detection with datasets that are only implicitly harmful. Our work studies robust detection mechanisms for adversarial use of fine-tuning APIs. We introduce the concept of a fine-tuning auditing agent and show it can detect harmful fine-tuning prior to model deployment. We provide our auditing agent with access to the fine-tuning dataset, as well as the fine-tuned and pre-fine-tuned models, and request the agent assigns a risk score for the fine-tuning job. We evaluate our detection approach on a diverse set of eight strong fine-tuning attacks from the literature, along with five benign fine-tuned models, totaling over 1400 independent audits. These attacks are undetectable with basic content moderation on the dataset, highlighting the challenge of the task. With the best set of affordances, our auditing agent achieves a 56.2% detection rate of adversarial fine-tuning at a 1% false positive rate. Most promising, the auditor is able to detect covert cipher attacks that evade safety evaluations and content moderation of the dataset. While benign fine-tuning with unintentional subtle safety degradation remains a challenge, we establish a baseline configuration for further work in this area. We release our auditing agent at https://github.com/safety-research/finetuning-auditor.