# Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

arXiv: https://arxiv.org/abs/2210.09545 · HTML: https://mlsanity.com/paper/2210.09545/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 41 of its 58 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 41)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Train longer, generalize better: closing the generalization gap in large batch training of neural networks](https://mlsanity.com/paper/1705.08741/) (2017)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://mlsanity.com/paper/2105.12400/) (2021)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [Clean-Label Backdoor Attacks on Video Recognition Models](https://mlsanity.com/paper/2003.03030/) (2020)
- [Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models](https://mlsanity.com/paper/1909.11299/) (2019)
- [Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness](https://mlsanity.com/paper/2005.00060/) (2020)
- [Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning](https://mlsanity.com/paper/2108.13888/) (2021)
- [Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models](https://mlsanity.com/paper/2103.15543/) (2021)
- [RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models](https://mlsanity.com/paper/2110.07831/) (2021)

## Built on by (most cited first, 30 of 57)

- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents](https://mlsanity.com/paper/2402.11208/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models](https://mlsanity.com/paper/2406.17092/) (2024)
- [Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts](https://mlsanity.com/paper/2407.15050/) (2024)
- [Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review](https://mlsanity.com/paper/2309.06055/) (2023)
- [A Pathway Towards Responsible AI Generated Content](https://mlsanity.com/paper/2303.01325/) (2023)
- [A Survey of Recent Backdoor Attacks and Defenses in Large Language Models](https://mlsanity.com/paper/2406.06852/) (2024)
- [PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning](https://mlsanity.com/paper/2410.08811/) (2024)
- [CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization](https://mlsanity.com/paper/2411.12768/) (2024)
- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [From Shortcuts to Triggers: Backdoor Defense with Denoised PoE](https://mlsanity.com/paper/2305.14910/) (2023)
- [Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation](https://mlsanity.com/paper/2410.14425/) (2024)
- [Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations](https://mlsanity.com/paper/2311.09763/) (2023)
- [BadActs: A Universal Backdoor Defense in the Activation Space](https://mlsanity.com/paper/2405.11227/) (2024)
- [Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2402.12168/) (2024)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models](https://mlsanity.com/paper/2405.07667/) (2024)
- [Exploring Vulnerabilities and Protections in Large Language Models: A Survey](https://mlsanity.com/paper/2406.00240/) (2024)
- [Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias](https://mlsanity.com/paper/2305.04547/) (2023)
- [Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space](https://mlsanity.com/paper/2402.12026/) (2024)
- [LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures](https://mlsanity.com/paper/2505.01177/) (2025)
- [A Systematic Review of Poisoning Attacks Against Large Language Models](https://mlsanity.com/paper/2506.06518/) (2025)
- [Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers](https://mlsanity.com/paper/2508.02175/) (2025)
- [Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference](https://mlsanity.com/paper/2603.13461/) (2026)
- [Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models](https://mlsanity.com/paper/2510.10265/) (2025)

## Abstract (arXiv)

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned samples. Although the clean weights of PLMs are readily available, existing methods have ignored this information in defending NLP models against backdoor attacks. In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models. Specifically, we leverage the clean pre-trained weights via two complementary techniques: (1) a two-step Fine-mixing technique, which first mixes the backdoored weights (fine-tuned on poisoned data) with the pre-trained weights, then fine-tunes the mixed weights on a small subset of clean data; (2) an Embedding Purification (E-PUR) technique, which mitigates potential backdoors existing in the word embeddings. We compare Fine-mixing with typical backdoor mitigation methods on three single-sentence sentiment classification tasks and two sentence-pair classification tasks and show that it outperforms the baselines by a considerable margin in all scenarios. We also show that our E-PUR method can benefit existing mitigation methods. Our work establishes a simple but strong baseline defense for secure fine-tuned NLP models against backdoor attacks.