Few-shot Backdoor Defense Using Shapley Estimation
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13348-13357
Abstract
Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis. However, prior works show that deep neural networks are easily manipulated into specific, attacker-decided behaviors in the inference stage by backdoor attacks which inject malicious small hidden triggers into model training, raising serious security threats. To determine the triggered neurons and protect against backdoor attacks, we exploit Shapley value and develop a new approach called Shapley Pruning (ShapPruning) that successfully mitigates backdoor attacks from models in a data-insufficient situation (1 image per class or even free of data). Considering the interaction between neurons, ShapPruning identifies the few infected neurons (under 1 % of all neurons) and manages to protect the model's structure and accuracy after pruning as many infected neurons as possible. To accelerate ShapPruning, we further propose discarding threshold and ∊ -greedy strategy to accelerate Shapley estimation, making it possible to repair poisoned models with only several minutes. Experiments demonstrate the effectiveness and robustness of our method against various attacks and tasks compared to existing methods.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U21B2045,U20A20223)
- Youth Innovation Promotion Association CAS (Y201929)
- ARC (FL-170100117)
This publication has 24 references indexed in Scilit:
- Trojaning Attack on Neural Networks2018
- Deep Residual Learning for Image Recognition2016
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures2015
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Polynomial calculation of the Shapley value based on samplingComputers & Operations Research, 2009
- Robust Discriminant Analysis Based on Nonparametric Maximum EntropyLecture Notes in Computer Science, 2009
- Empirical Bernstein stopping2008
- Alternatives to the Median Absolute DeviationJournal of the American Statistical Association, 1993
- Optimized Monte Carlo Data AnalysisComputers in Physics, 1989
- 17. A Value for n-Person Games1953