# Towards A Proactive ML Approach for Detecting Backdoor Poison Samples

arXiv: https://arxiv.org/abs/2205.13616 · HTML: https://mlsanity.com/paper/2205.13616/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 81 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [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)
- [The Implicit Bias of Gradient Descent on Separable Data](https://mlsanity.com/paper/1710.10345/) (2017)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [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)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [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)
- [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)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [Blind Backdoors in Deep Learning Models](https://mlsanity.com/paper/2005.03823/) (2020)
- [Surrogate Gap Minimization Improves Sharpness-Aware Training](https://mlsanity.com/paper/2203.08065/) (2022)

## Built on by (most cited first, 30 of 40)

- [Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples](https://mlsanity.com/paper/2307.10562/) (2023)
- [ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms](https://mlsanity.com/paper/2302.11408/) (2023)
- [Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack](https://mlsanity.com/paper/2405.16134/) (2024)
- [BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning](https://mlsanity.com/paper/2407.19845/) (2024)
- [AI Risk Management Should Incorporate Both Safety and Security](https://mlsanity.com/paper/2405.19524/) (2024)
- [Defenses in Adversarial Machine Learning: A Survey](https://mlsanity.com/paper/2312.08890/) (2023)
- [BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection](https://mlsanity.com/paper/2308.12439/) (2023)
- [Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor](https://mlsanity.com/paper/2405.16112/) (2024)
- [Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers](https://mlsanity.com/paper/2306.00816/) (2023)
- [VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models](https://mlsanity.com/paper/2309.16211/) (2023)
- [SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs](https://mlsanity.com/paper/2506.04743/) (2025)
- [BAN: Detecting Backdoors Activated by Adversarial Neuron Noise](https://mlsanity.com/paper/2405.19928/) (2024)
- [FLARE: Toward Universal Dataset Purification against Backdoor Attacks](https://mlsanity.com/paper/2411.19479/) (2024)
- [Towards Backdoor Stealthiness in Model Parameter Space](https://mlsanity.com/paper/2501.05928/) (2025)
- [Invisible Backdoor Attack against Self-supervised Learning](https://mlsanity.com/paper/2405.14672/) (2024)
- [Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness](https://mlsanity.com/paper/2405.20291/) (2024)
- [Neutralizing Backdoors through Information Conflicts for Large Language Models](https://mlsanity.com/paper/2411.18280/) (2024)
- [DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data](https://mlsanity.com/paper/2503.21305/) (2025)
- [Clean-Label Physical Backdoor Attacks with Data Distillation](https://mlsanity.com/paper/2407.19203/) (2024)
- [Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection](https://mlsanity.com/paper/2403.15955/) (2024)
- [BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation](https://mlsanity.com/paper/2411.11006/) (2024)
- [Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets](https://mlsanity.com/paper/2504.11990/) (2025)
- [Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking](https://mlsanity.com/paper/2312.07955/) (2023)
- [Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning](https://mlsanity.com/paper/2407.05112/) (2024)
- [SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach](https://mlsanity.com/paper/2505.14531/) (2025)
- [Protecting against simultaneous data poisoning attacks](https://mlsanity.com/paper/2408.13221/) (2024)
- [Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models](https://mlsanity.com/paper/2411.09540/) (2024)
- [Trust Under Siege: Label Spoofing Attacks against Machine Learning for Android Malware Detection](https://mlsanity.com/paper/2503.11841/) (2025)
- [On the Security Risks of ML-based Malware Detection Systems: A Survey](https://mlsanity.com/paper/2505.10903/) (2025)
- [AutoDetect: Designing an Autoencoder-based Detection Method for Poisoning Attacks on Object Detection Applications in the Military Domain](https://mlsanity.com/paper/2509.03179/) (2025)

## Abstract (arXiv)

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we uncover a post-hoc workflow underlying most prior work, where defenders passively allow the attack to proceed and then leverage the characteristics of the post-attacked model to uncover poison samples. We reveal that this workflow does not fully exploit defenders' capabilities, and defense pipelines built on it are prone to failure or performance degradation in many scenarios. Second, we suggest a paradigm shift by promoting a proactive mindset in which defenders engage proactively with the entire model training and poison detection pipeline, directly enforcing and magnifying distinctive characteristics of the post-attacked model to facilitate poison detection. Based on this, we formulate a unified framework and provide practical insights on designing detection pipelines that are more robust and generalizable. Third, we introduce the technique of Confusion Training (CT) as a concrete instantiation of our framework. CT applies an additional poisoning attack to the already poisoned dataset, actively decoupling benign correlation while exposing backdoor patterns to detection. Empirical evaluations on 4 datasets and 14 types of attacks validate the superiority of CT over 14 baseline defenses.