# Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders

arXiv: https://arxiv.org/abs/2406.03508 · HTML: https://mlsanity.com/paper/2406.03508/

## Key facts

- Cited by 8 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 45 of its 71 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)
- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements](https://mlsanity.com/paper/2006.01043/) (2020)
- [Adversarial Unlearning of Backdoors via Implicit Hypergradient](https://mlsanity.com/paper/2110.03735/) (2021)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Backdoor Defense via Decoupling the Training Process](https://mlsanity.com/paper/2202.03423/) (2022)
- [Poisoning and Backdooring Contrastive Learning](https://mlsanity.com/paper/2106.09667/) (2021)
- [Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness](https://mlsanity.com/paper/2005.00060/) (2020)

## Built on by (most cited first, 8 of 8)

- [Eliminating Backdoors in Neural Code Models for Secure Code Understanding](https://mlsanity.com/paper/2408.04683/) (2024)
- [When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters](https://mlsanity.com/paper/2602.21977/) (2026)
- [Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets](https://mlsanity.com/paper/2504.11990/) (2025)
- [Seal Your Backdoor with Variational Defense](https://mlsanity.com/paper/2503.08829/) (2025)
- [A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories](https://mlsanity.com/paper/2505.01067/) (2025)
- [Secure Resource Allocation via Constrained Deep Reinforcement Learning](https://mlsanity.com/paper/2501.11557/) (2025)
- [The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training](https://mlsanity.com/paper/2606.29451/) (2026)
- [FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation](https://mlsanity.com/paper/2608.26861/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performance. The pre-trained encoders by SSL, however, are vulnerable to backdoor attacks as demonstrated by existing studies. Numerous backdoor mitigation techniques are designed for downstream task models. However, their effectiveness is impaired and limited when adapted to pre-trained encoders, due to the lack of label information when pre-training. To address backdoor attacks against pre-trained encoders, in this paper, we innovatively propose a mutual information guided backdoor mitigation technique, named MIMIC. MIMIC treats the potentially backdoored encoder as the teacher net and employs knowledge distillation to distill a clean student encoder from the teacher net. Different from existing knowledge distillation approaches, MIMIC initializes the student with random weights, inheriting no backdoors from teacher nets. Then MIMIC leverages mutual information between each layer and extracted features to locate where benign knowledge lies in the teacher net, with which distillation is deployed to clone clean features from teacher to student. We craft the distillation loss with two aspects, including clone loss and attention loss, aiming to mitigate backdoors and maintain encoder performance at the same time. Our evaluation conducted on two backdoor attacks in SSL demonstrates that MIMIC can significantly reduce the attack success rate by only utilizing <5% of clean data, surpassing seven state-of-the-art backdoor mitigation techniques.