# Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation

arXiv: https://arxiv.org/abs/2204.09975 · HTML: https://mlsanity.com/paper/2204.09975/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 21 Apr 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [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)
- [SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems](https://mlsanity.com/paper/1812.00292/) (2018)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [Backdoor Attacks Against Deep Learning Systems in the Physical World](https://mlsanity.com/paper/2006.14580/) (2020)
- [Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness](https://mlsanity.com/paper/2005.00060/) (2020)
- [Adversarially Robust Distillation](https://mlsanity.com/paper/1905.09747/) (2019)
- [Rethinking the Trigger of Backdoor Attack](https://mlsanity.com/paper/2004.04692/) (2020)
- [Pay attention to the activations: a modular attention mechanism for fine-grained image recognition](https://mlsanity.com/paper/1907.13075/) (2019)
- [FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications](https://mlsanity.com/paper/2006.15632/) (2020)
- [Interpreting and Disentangling Feature Components of Various Complexity from DNNs](https://mlsanity.com/paper/2006.15920/) (2020)

## Built on by (most cited first, 18 of 18)

- [Label Poisoning is All You Need](https://mlsanity.com/paper/2310.18933/) (2023)
- [BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning](https://mlsanity.com/paper/2407.19845/) (2024)
- [Backdoor Cleansing with Unlabeled Data](https://mlsanity.com/paper/2211.12044/) (2022)
- [Understanding the Gains from Repeated Self-Distillation](https://mlsanity.com/paper/2407.04600/) (2024)
- [WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks](https://mlsanity.com/paper/2310.11595/) (2023)
- [Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders](https://mlsanity.com/paper/2406.03508/) (2024)
- [Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data](https://mlsanity.com/paper/2310.06372/) (2023)
- [INK: Inheritable Natural Backdoor Attack Against Model Distillation](https://mlsanity.com/paper/2304.10985/) (2023)
- [Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios](https://mlsanity.com/paper/2306.08011/) (2023)
- [Temporal-Distributed Backdoor Attack Against Video Based Action Recognition](https://mlsanity.com/paper/2308.11070/) (2023)
- [Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model](https://mlsanity.com/paper/2406.03409/) (2024)
- [Backdoor Mitigation by Correcting the Distribution of Neural Activations](https://mlsanity.com/paper/2308.09850/) (2023)
- [Invisible Backdoor Attack Through Singular Value Decomposition](https://mlsanity.com/paper/2403.13018/) (2024)
- [Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models](https://mlsanity.com/paper/2411.09540/) (2024)
- [Trojan Cleansing with Neural Collapse](https://mlsanity.com/paper/2411.12914/) (2024)
- [BadScan: An Architectural Backdoor Attack on Visual State Space Models](https://mlsanity.com/paper/2411.17283/) (2024)
- [SATBA: An Invisible Backdoor Attack Based On Spatial Attention](https://mlsanity.com/paper/2302.13056/) (2023)
- [BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning](https://mlsanity.com/paper/2401.15002/) (2024)

## Abstract (arXiv)

Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers from non-negligible Attack Success Rate (ASR) together with lowered classification ACCuracy (ACC), since NAD focuses on backdoor defense using attention features (i.e., attention maps) of the same order. In this paper, we introduce a novel backdoor defense framework named Attention Relation Graph Distillation (ARGD), which fully explores the correlation among attention features with different orders using our proposed Attention Relation Graphs (ARGs). Based on the alignment of ARGs between both teacher and student models during knowledge distillation, ARGD can eradicate more backdoor triggers than NAD. Comprehensive experimental results show that, against six latest backdoor attacks, ARGD outperforms NAD by up to 94.85% reduction in ASR, while ACC can be improved by up to 3.23%.