NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
원문 초록
Deep neural networks have achieved state-of-the-art performance on various tasks. However, lack of interpretability and transparency makes it easier for malicious attackers to inject trojan backdoor into the neural networks, which will make the model behave abnormally when a backdoor sample with a specific trigger is input. In this paper, we propose NeuronInspect, a framework to detect trojan backdoors in deep neural networks via output explanation techniques. NeuronInspect first identifies the existence of backdoor attack targets by generating the explanation heatmap of the output layer. We observe that generated heatmaps from clean and backdoored models have different characteristics. Therefore we extract features that measure the attributes of explanations from an attacked model namely: sparse, smooth and persistent. We combine these features and use outlier detection to figure out the outliers, which is the set of attack targets. We demonstrate the effectiveness and efficiency of NeuronInspect on MNIST digit recognition dataset and GTSRB traffic sign recognition dataset. We extensively evaluate NeuronInspect on different attack scenarios and prove better robustness and effectiveness over state-of-the-art trojan backdoor detection techniques Neural Cleanse by a great margin.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Backdooring Outlier Detection Methods: A Novel Attack Approach
LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
Robust Spatiotemporal Epidemic Modeling with Integrated Adaptive Outlier Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.