# Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer

arXiv: https://arxiv.org/abs/2208.06592 · HTML: https://mlsanity.com/paper/2208.06592/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 13 Aug 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [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)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [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)
- [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)
- [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)
- [Clean-Label Backdoor Attacks on Video Recognition Models](https://mlsanity.com/paper/2003.03030/) (2020)
- [Dynamic Backdoor Attacks Against Machine Learning Models](https://mlsanity.com/paper/2003.03675/) (2020)
- [Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs](https://mlsanity.com/paper/1906.10842/) (2019)
- [A vector-contraction inequality for Rademacher complexities](https://mlsanity.com/paper/1605.00251/) (2016)
- [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)
- [SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics](https://mlsanity.com/paper/2104.11315/) (2021)
- [Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review](https://mlsanity.com/paper/2007.10760/) (2020)
- [Backdoor Scanning for Deep Neural Networks through K-Arm Optimization](https://mlsanity.com/paper/2102.05123/) (2021)
- [An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks](https://mlsanity.com/paper/2006.08131/) (2020)
- [Bypassing Backdoor Detection Algorithms in Deep Learning](https://mlsanity.com/paper/1905.13409/) (2019)
- [Model Agnostic Defence against Backdoor Attacks in Machine Learning](https://mlsanity.com/paper/1908.02203/) (2019)

## Abstract (arXiv)

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the backdoor trigger is usually of small size or affects the activation of only a few neurons. However, the above observations are violated in many cases especially for advanced backdoor attacks, hindering the performance and applicability of the existing defenses. In this paper, we propose a backdoor defense DTInspector built upon a new observation. That is, an effective backdoor attack usually requires high prediction confidence on the poisoned training samples, so as to ensure that the trained model exhibits the targeted behavior with a high probability. Based on this observation, DTInspector first learns a patch that could change the predictions of most high-confidence data, and then decides the existence of backdoor by checking the ratio of prediction changes after applying the learned patch on the low-confidence data. Extensive evaluations on five backdoor attacks, four datasets, and three advanced attacking types demonstrate the effectiveness of the proposed defense.