# Anti-Backdoor Learning: Training Clean Models on Poisoned Data

arXiv: https://arxiv.org/abs/2110.11571 · HTML: https://mlsanity.com/paper/2110.11571/

## Key facts

- Cited by 263 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 22 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (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)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (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)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [A new Backdoor Attack in CNNs by training set corruption without label poisoning](https://mlsanity.com/paper/1902.11237/) (2019)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [Clean-Label Backdoor Attacks on Video Recognition Models](https://mlsanity.com/paper/2003.03030/) (2020)
- [Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs](https://mlsanity.com/paper/1906.10842/) (2019)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness](https://mlsanity.com/paper/2005.00060/) (2020)
- [Transferable Clean-Label Poisoning Attacks on Deep Neural Nets](https://mlsanity.com/paper/1905.05897/) (2019)
- [SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics](https://mlsanity.com/paper/2104.11315/) (2021)
- [Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection](https://mlsanity.com/paper/1908.00686/) (2019)
- [Backdoor Scanning for Deep Neural Networks through K-Arm Optimization](https://mlsanity.com/paper/2102.05123/) (2021)
- [Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification](https://mlsanity.com/paper/2012.11212/) (2020)
- [Rethinking the Trigger of Backdoor Attack](https://mlsanity.com/paper/2004.04692/) (2020)
- [Do We Need Zero Training Loss After Achieving Zero Training Error?](https://mlsanity.com/paper/2002.08709/) (2020)
- [What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space](https://mlsanity.com/paper/2101.06898/) (2021)

## Built on by (most cited first, 30 of 263)

- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [BackdoorBench: A Comprehensive Benchmark of Backdoor Learning](https://mlsanity.com/paper/2206.12654/) (2022)
- [BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning](https://mlsanity.com/paper/2311.12075/) (2023)
- [Federated Learning with Label Distribution Skew via Logits Calibration](https://mlsanity.com/paper/2209.00189/) (2022)
- [Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information](https://mlsanity.com/paper/2204.05255/) (2022)
- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [Black-box Dataset Ownership Verification via Backdoor Watermarking](https://mlsanity.com/paper/2209.06015/) (2022)
- [Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization](https://mlsanity.com/paper/2304.11823/) (2023)
- [CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.03323/) (2023)
- [Instruction Backdoor Attacks Against Customized LLMs](https://mlsanity.com/paper/2402.09179/) (2024)
- [Reconstructive Neuron Pruning for Backdoor Defense](https://mlsanity.com/paper/2305.14876/) (2023)
- [Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models](https://mlsanity.com/paper/2210.09545/) (2022)
- [BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models](https://mlsanity.com/paper/2408.12798/) (2024)
- [UNICORN: A Unified Backdoor Trigger Inversion Framework](https://mlsanity.com/paper/2304.02786/) (2023)
- [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)
- [Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples](https://mlsanity.com/paper/2307.10562/) (2023)
- [Few-shot Backdoor Defense Using Shapley Estimation](https://mlsanity.com/paper/2112.14889/) (2021)
- [Towards A Proactive ML Approach for Detecting Backdoor Poison Samples](https://mlsanity.com/paper/2205.13616/) (2022)
- [Test-Time Backdoor Attacks on Multimodal Large Language Models](https://mlsanity.com/paper/2402.08577/) (2024)
- [Rethinking the Reverse-engineering of Trojan Triggers](https://mlsanity.com/paper/2210.15127/) (2022)
- [IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency](https://mlsanity.com/paper/2405.09786/) (2024)
- [Training with More Confidence: Mitigating Injected and Natural Backdoors During Training](https://mlsanity.com/paper/2202.06382/) (2022)
- [Fine-Tuning Is All You Need to Mitigate Backdoor Attacks](https://mlsanity.com/paper/2212.09067/) (2022)
- [Backdoor Defense via Deconfounded Representation Learning](https://mlsanity.com/paper/2303.06818/) (2023)
- [Few-Shot Backdoor Attacks on Visual Object Tracking](https://mlsanity.com/paper/2201.13178/) (2022)
- [Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection](https://mlsanity.com/paper/2402.11473/) (2024)
- [BadMerging: Backdoor Attacks Against Model Merging](https://mlsanity.com/paper/2408.07362/) (2024)

## Abstract (arXiv)

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training methods can be devised to prevent the backdoor triggers being injected into the trained model in the first place. In this paper, we introduce the concept of anti-backdoor learning, aiming to train clean models given backdoor-poisoned data. We frame the overall learning process as a dual-task of learning the clean and the backdoor portions of data. From this view, we identify two inherent characteristics of backdoor attacks as their weaknesses: 1) the models learn backdoored data much faster than learning with clean data, and the stronger the attack the faster the model converges on backdoored data; 2) the backdoor task is tied to a specific class (the backdoor target class). Based on these two weaknesses, we propose a general learning scheme, Anti-Backdoor Learning (ABL), to automatically prevent backdoor attacks during training. ABL introduces a two-stage gradient ascent mechanism for standard training to 1) help isolate backdoor examples at an early training stage, and 2) break the correlation between backdoor examples and the target class at a later training stage. Through extensive experiments on multiple benchmark datasets against 10 state-of-the-art attacks, we empirically show that ABL-trained models on backdoor-poisoned data achieve the same performance as they were trained on purely clean data. Code is available at urlhttps://github.com/bboylyg/ABL.