Litcius/Paper detail

DNNGuard: An Elastic Heterogeneous DNN Accelerator Architecture against Adversarial Attacks

Xingbin Wang, Rui Hou, Boyan Zhao, Fengkai Yuan, Jun Zhang, Dan Meng, Xuehai Qian

202032 citationsDOIOpen Access PDF

Abstract

Recent studies show that Deep Neural Networks (DNN) are vulnerable to adversarial samples that are generated by perturbing correctly classified inputs to cause the misclassification of DNN models. This can potentially lead to disastrous consequences, especially in security-sensitive applications such as unmanned vehicles, finance and healthcare. Existing adversarial defense methods require a variety of computing units to effectively detect the adversarial samples. However, deploying adversary sample defense methods in existing DNN accelerators leads to many key issues in terms of cost, computational efficiency and information security. Moreover, existing DNN accelerators cannot provide effective support for special computation required in the defense methods.

Topics & Concepts

Adversarial systemAdversaryComputer scienceDeep neural networksComputationVariety (cybernetics)Artificial neural networkKey (lock)Artificial intelligenceSample (material)ArchitectureMachine learningComputer securityDistributed computingComputer engineeringAlgorithmChromatographyArtVisual artsChemistryAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsAdvanced Malware Detection Techniques
DNNGuard: An Elastic Heterogeneous DNN Accelerator Architecture against Adversarial Attacks | Litcius