An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks
Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. In a successful adversarial attack, the targeted mis-classification should be achieved with the minimal distortion added. In the literature, the added distortions are usually measured by L0, L1, L2, and L infinity norms, namely, L0, L1, L2, and L infinity attacks, respectively. However, there lacks a versatile framework for all types of adversarial attacks. This work for the first time unifies the methods of generating adversarial examples by leveraging ADMM (Alternating Direction Method of Multipliers), an operator splitting optimization approach, such that L0, L1, L2, and L infinity attacks can be effectively implemented by this general framework with little modifications. Comparing with the state-of-the-art attacks in each category, our ADMM-based attacks are so far the strongest, achieving both the 100% attack success rate and the minimal distortion.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse …
Adversarial AttackBayesian Optimizationimage-classificationImage ClassificationDetecting Shared Data Manipulation in Distributed Optimization Algorithms
This paper investigates the vulnerability of the Alternating Direction Method of Multipliers (ADMM) algorithm to shared data manipulation, with a focus on solving optimal power flow (OPF) problems. Deliberate data manipu…
Bilevel OptimizationDistributed OptimizationGeneralizing Universal Adversarial Attacks Beyond Additive Perturbations
The previous study has shown that universal adversarial attacks can fool deep neural networks over a large set of input images with a single human-invisible perturbation. However, current methods for universal adversaria…
Adversarial AttackADMM based Distributed State Observer Design under Sparse Sensor Attacks
This paper considers the design of a distributed state-observer for discrete-time Linear Time-Invariant (LTI) systems in the presence of sensor attacks. We assume there is a network of observer nodes, communicating with …
Adversarial AttackOn The Relationship Between Universal Adversarial Attacks And Sparse Representations
The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at expl…
Sensitivity