Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection
- 19 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 4668-4680
Abstract
This paper proposes a data-efficient detection method for deep neural networks against backdoor attacks under a black-box scenario. The proposed approach is motivated by the intuition that features corresponding to triggers have a higher influence in determining the backdoored network output than any other benign features. To quantitatively measure the effects of triggers and benign features on determining the backdoored network output, we introduce five metrics. To calculate the five-metric values for a given input, we first generate several synthetic samples by injecting the input’s partial contents into clean validation samples. Then, the five metrics are computed by using the output labels of the corresponding synthetic samples. One contribution of this work is the use of a tiny clean validation dataset. Having the computed five metrics, five novelty detectors are trained from the validation dataset. A meta novelty detector fuses the output of the five trained novelty detectors to generate a meta confidence score. During online testing, our method determines if online samples are poisoned or not via assessing their meta confidence scores output by the meta novelty detector. We show the efficacy of our methodology through a broad range of backdoor attacks, including ablation studies and comparison to existing approaches. Our methodology is promising since the proposed five metrics quantify the inherent differences between clean and poisoned samples. Additionally, our detection method can be incrementally improved by appending more metrics that may be proposed to address future advanced attacks.Keywords
All Related Versions
Funding Information
- Army Research Office (W911NF-21-1-0155)
- Center for Artificial Intelligence and Robotics, New York University Abu Dhabi (NYUAD), funded by Tamkeen through the NYUAD Research Institute (CG010)
This publication has 57 references indexed in Scilit:
- Learning deep event models for crowd anomaly detectionNeurocomputing, 2017
- Deep Residual Learning for Image Recognition2016
- DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving2015
- Deep Learning Face Representation from Predicting 10,000 Classes2014
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012
- Face recognition in unconstrained videos with matched background similarity2011
- Sparse reconstruction cost for abnormal event detection2011
- Random ForestsMachine Learning, 2001
- LOF2000