# Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks

arXiv: https://arxiv.org/abs/2508.17158 · HTML: https://mlsanity.com/paper/2508.17158/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 23 Aug 2025.

## Builds on (most cited first, 30 of 33)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (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)
- [Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications](https://mlsanity.com/paper/2402.05162/) (2024)
- [Removing RLHF Protections in GPT-4 via Fine-Tuning](https://mlsanity.com/paper/2311.05553/) (2023)
- [Tamper-Resistant Safeguards for Open-Weight LLMs](https://mlsanity.com/paper/2408.00761/) (2024)
- [Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models](https://mlsanity.com/paper/2405.16833/) (2024)
- [What is in Your Safe Data? Identifying Benign Data that Breaks Safety](https://mlsanity.com/paper/2404.01099/) (2024)
- [Representation Noising: A Defence Mechanism Against Harmful Finetuning](https://mlsanity.com/paper/2405.14577/) (2024)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation](https://mlsanity.com/paper/2406.20053/) (2024)
- [Robustifying Safety-Aligned Large Language Models through Clean Data Curation](https://mlsanity.com/paper/2405.19358/) (2024)
- [A safety realignment framework via subspace-oriented model fusion for large language models](https://mlsanity.com/paper/2405.09055/) (2024)
- [BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B](https://mlsanity.com/paper/2311.00117/) (2023)
- [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)
- [Exploiting Novel GPT-4 APIs](https://mlsanity.com/paper/2312.14302/) (2023)
- [ProteinBench: A Holistic Evaluation of Protein Foundation Models](https://mlsanity.com/paper/2409.06744/) (2024)

## Built on by (most cited first, 11 of 11)

- [Building Production-Ready Probes For Gemini](https://mlsanity.com/paper/2601.11516/) (2026)
- [Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks](https://mlsanity.com/paper/2601.04603/) (2026)
- [Introspection Adapters: Training LLMs to Report Their Learned Behaviors](https://mlsanity.com/paper/2604.16812/) (2026)
- [All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language](https://mlsanity.com/paper/2510.09714/) (2025)
- [Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink](https://mlsanity.com/paper/2602.05228/) (2026)
- [Detecting Adversarial Fine-tuning with Auditing Agents](https://mlsanity.com/paper/2510.16255/) (2025)
- [Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models](https://mlsanity.com/paper/2601.22818/) (2026)
- [Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning](https://mlsanity.com/paper/2603.29038/) (2026)
- [Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning](https://mlsanity.com/paper/2609.09553/) (2026)
- [Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guards](https://mlsanity.com/paper/2609.26178/) (2026)
- [LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations](https://mlsanity.com/paper/2609.32717/) (2026)

## Abstract (arXiv)

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful content in seemingly harmless fine-tuning data, evading both human monitoring and standard content filters. We formalize the fine-tuning API defense problem, and introduce the Cipher Fine-tuning Robustness benchmark (CIFR), a benchmark for evaluating defense strategies' ability to retain model safety in the face of cipher-enabled attackers while achieving the desired level of fine-tuning functionality. We include diverse cipher encodings and families, with some kept exclusively in the test set to evaluate for generalization across unseen ciphers and cipher families. We then evaluate different defenses on the benchmark and train probe monitors on model internal activations from multiple fine-tunes. We show that probe monitors achieve over 99% detection accuracy, generalize to unseen cipher variants and families, and compare favorably to state-of-the-art monitoring approaches. We open-source CIFR and the code to reproduce our experiments to facilitate further research in this critical area. Code and data are available online https://github.com/JackYoustra/safe-finetuning-api