# Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

arXiv: https://arxiv.org/abs/2210.06428 · HTML: https://mlsanity.com/paper/2210.06428/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 75 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (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)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Invisible Backdoor Attack with Sample-Specific Triggers](https://mlsanity.com/paper/2012.03816/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [A new Backdoor Attack in CNNs by training set corruption without label poisoning](https://mlsanity.com/paper/1902.11237/) (2019)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [Adversarial Unlearning of Backdoors via Implicit Hypergradient](https://mlsanity.com/paper/2110.03735/) (2021)
- [Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective](https://mlsanity.com/paper/2104.03413/) (2021)
- [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)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems](https://mlsanity.com/paper/1908.01763/) (2019)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information](https://mlsanity.com/paper/2204.05255/) (2022)
- [Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy](https://mlsanity.com/paper/1911.07116/) (2019)

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

- [Black-box Backdoor Defense via Zero-shot Image Purification](https://mlsanity.com/paper/2303.12175/) (2023)
- [Backdoor Defense via Adaptively Splitting Poisoned Dataset](https://mlsanity.com/paper/2303.12993/) (2023)
- [Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots](https://mlsanity.com/paper/2310.18633/) (2023)
- [Revisiting Data-Free Knowledge Distillation with Poisoned Teachers](https://mlsanity.com/paper/2306.02368/) (2023)
- [On the Difficulty of Defending Contrastive Learning against Backdoor Attacks](https://mlsanity.com/paper/2312.09057/) (2023)
- [Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment](https://mlsanity.com/paper/2411.15673/) (2024)
- [Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models](https://mlsanity.com/paper/2510.10265/) (2025)
- [Safe and Robust Watermark Injection with a Single OoD Image](https://mlsanity.com/paper/2309.01786/) (2023)
- [Protecting against simultaneous data poisoning attacks](https://mlsanity.com/paper/2408.13221/) (2024)
- [Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers](https://mlsanity.com/paper/2410.01128/) (2024)
- [Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors](https://mlsanity.com/paper/2603.09772/) (2026)
- [Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling](https://mlsanity.com/paper/2608.00732/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor samples. In this paper, we propose a brand-new backdoor defense strategy, which makes it much easier to remove the harmful influence of backdoor samples from the model. Our defense strategy, Trap and Replace, consists of two stages. In the first stage, we bait and trap the backdoors in a small and easy-to-replace subnetwork. Specifically, we add an auxiliary image reconstruction head on top of the stem network shared with a light-weighted classification head. The intuition is that the auxiliary image reconstruction task encourages the stem network to keep sufficient low-level visual features that are hard to learn but semantically correct, instead of overfitting to the easy-to-learn but semantically incorrect backdoor correlations. As a result, when trained on backdoored datasets, the backdoors are easily baited towards the unprotected classification head, since it is much more vulnerable than the shared stem, leaving the stem network hardly poisoned. In the second stage, we replace the poisoned light-weighted classification head with an untainted one, by re-training it from scratch only on a small holdout dataset with clean samples, while fixing the stem network. As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples. We evaluate our method against ten different backdoor attacks. Our method outperforms previous state-of-the-art methods by up to 20.57%, 9.80%, and 13.72% attack success rate and on-average 3.14%, 1.80%, and 1.21% clean classification accuracy on CIFAR10, GTSRB, and ImageNet-12, respectively. Code is available online.