# Backdoor Attack in the Physical World

arXiv: https://arxiv.org/abs/2104.02361 · HTML: https://mlsanity.com/paper/2104.02361/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Label-Consistent Backdoor Attacks](https://mlsanity.com/paper/1912.02771/) (2019)
- [Clean-Label Backdoor Attacks on Video Recognition Models](https://mlsanity.com/paper/2003.03030/) (2020)
- [Neural Trojans](https://mlsanity.com/paper/1710.00942/) (2017)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review](https://mlsanity.com/paper/2007.10760/) (2020)
- [Backdoor Attack against Speaker Verification](https://mlsanity.com/paper/2010.11607/) (2020)

## Built on by (most cited first, 30 of 84)

- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Adversarial Unlearning of Backdoors via Implicit Hypergradient](https://mlsanity.com/paper/2110.03735/) (2021)
- [Backdoor Defense via Decoupling the Training Process](https://mlsanity.com/paper/2202.03423/) (2022)
- [Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information](https://mlsanity.com/paper/2204.05255/) (2022)
- [Black-box Dataset Ownership Verification via Backdoor Watermarking](https://mlsanity.com/paper/2209.06015/) (2022)
- [Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand](https://mlsanity.com/paper/2310.14942/) (2023)
- [Defending against Model Stealing via Verifying Embedded External Features](https://mlsanity.com/paper/2112.03476/) (2021)
- [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)
- [An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences](https://mlsanity.com/paper/2111.08429/) (2021)
- [Test-Time Backdoor Attacks on Multimodal Large Language Models](https://mlsanity.com/paper/2402.08577/) (2024)
- [IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency](https://mlsanity.com/paper/2405.09786/) (2024)
- [Few-Shot Backdoor Attacks on Visual Object Tracking](https://mlsanity.com/paper/2201.13178/) (2022)
- [Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2111.12965/) (2021)
- [Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound](https://mlsanity.com/paper/2307.08208/) (2023)
- [BackdoorBox: A Python Toolbox for Backdoor Learning](https://mlsanity.com/paper/2302.01762/) (2023)
- [Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World](https://mlsanity.com/paper/2201.08619/) (2022)
- [REFINE: Inversion-Free Backdoor Defense via Model Reprogramming](https://mlsanity.com/paper/2502.18508/) (2025)
- [Robust Backdoor Attacks against Deep Neural Networks in Real Physical World](https://mlsanity.com/paper/2104.07395/) (2021)
- [Backdoor Attack with Sparse and Invisible Trigger](https://mlsanity.com/paper/2306.06209/) (2023)
- [PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning](https://mlsanity.com/paper/2202.03609/) (2022)
- [Defending Against Backdoor Attacks by Layer-wise Feature Analysis](https://mlsanity.com/paper/2302.12758/) (2023)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [Persistent Backdoor Attacks in Continual Learning](https://mlsanity.com/paper/2409.13864/) (2024)
- [Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis](https://mlsanity.com/paper/2210.10886/) (2022)
- [BATT: Backdoor Attack with Transformation-based Triggers](https://mlsanity.com/paper/2211.01806/) (2022)
- [BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection](https://mlsanity.com/paper/2308.12439/) (2023)
- [Backdoor Attacks on Crowd Counting](https://mlsanity.com/paper/2207.05641/) (2022)
- [Backdoor Defense via Suppressing Model Shortcuts](https://mlsanity.com/paper/2211.05631/) (2022)
- [Towards Robust Model Watermark via Reducing Parametric Vulnerability](https://mlsanity.com/paper/2309.04777/) (2023)

## Abstract (arXiv)

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently, most existing backdoor attacks adopted the setting of static trigger, i.e., triggers across the training and testing images follow the same appearance and are located in the same area. In this paper, we revisit this attack paradigm by analyzing trigger characteristics. We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training. As such, those attacks are far less effective in the physical world, where the location and appearance of the trigger in the digitized image may be different from that of the one used for training. Moreover, we also discuss how to alleviate such vulnerability. We hope that this work could inspire more explorations on backdoor properties, to help the design of more advanced backdoor attack and defense methods.