DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
Han Qiu, Yi Zeng, Shangwei Guo, Tianwei Zhang, Meikang Qiu, Bhavani Thuraisingham
Abstract
Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can inject poisoned samples into the datasets or embed backdoors in those models. Such an integrity breach can cause severe consequences, especially in safety- and security-critical applications. Various backdoor attack techniques have been proposed for higher effectiveness and stealthiness. Unfortunately, existing defense solutions are not practical to thwart those attacks in a comprehensive way.
Topics & Concepts
BackdoorComputer scienceComputer securityAdversarial systemArtificial intelligenceAdversarial Robustness in Machine LearningNetwork Security and Intrusion DetectionAnomaly Detection Techniques and Applications