Block Switching: A Stochastic Approach for Deep Learning Security
Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions, while maintain imperceptible to human vision system. In this paper, we introduce Block Switching (BS), a defense strategy against adversarial attacks based on stochasticity. BS replaces a block of model layers with multiple parallel channels, and the active channel is randomly assigned in the run time hence unpredictable to the adversary. We show empirically that BS leads to a more dispersed input gradient distribution and superior defense effectiveness compared with other stochastic defenses such as stochastic activation pruning (SAP). Compared to other defenses, BS is also characterized by the following features: (i) BS causes less test accuracy drop; (ii) BS is attack-independent and (iii) BS is compatible with other defenses and can be used jointly with others.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks
According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns …
Adversarial AttackBIG-bench Machine LearningSelf-Driving CarsExact and Evolutionary Algorithms for Sequential Multi-Objective Transmission Topology Planning
We study day-ahead transmission topology control for high-voltage grid operation under $N-1$ security constraints. The operational task is to select, over a 24-hour horizon, a sequence of substation topologies obtained v…
Decision MakingSpectral clustering in the dynamic stochastic block model
In the present paper, we studied a Dynamic Stochastic Block Model (DSBM) under the assumptions that the connection probabilities, as functions of time, are smooth and that at most $s$ nodes can switch their class members…
ClusteringmodelStochastic Block ModelAlternative models for FX: pricing double barrier options in regime-switching Lévy models with memory
This paper is a supplement to our recent paper ``Alternative models for FX, arbitrage opportunities and efficient pricing of double barrier options in L\'evy models". We introduce the class of regime-switching L\'evy mod…
Stabilization of Microbial Communities by Responsive Phenotypic Switching
Clonal microbes can switch between different phenotypes and recent theoretical work has shown that stochastic switching between these subpopulations can stabilize microbial communities. This phenotypic switching need not…