Adversarial Attack Based on Prediction-Correction
Deep neural networks (DNNs) are vulnerable to adversarial examples obtained by adding small perturbations to original examples. The added perturbations in existing attacks are mainly determined by the gradient of the loss function with respect to the inputs. In this paper, the close relationship between gradient-based attacks and the numerical methods for solving ordinary differential equation (ODE) is studied for the first time. Inspired by the numerical solution of ODE, a new prediction-correction (PC) based adversarial attack is proposed. In our proposed PC-based attack, some existing attack can be selected to produce a predicted example first, and then the predicted example and the current example are combined together to determine the added perturbations. The proposed method possesses good extensibility and can be applied to all available gradient-based attacks easily. Extensive experiments demonstrate that compared with the state-of-the-art gradient-based adversarial attacks, our proposed PC-based attacks have higher attack success rates, and exhibit better transferability.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackPredictionSimilar Papers 제목 키워드 기반
Adversarial Detection and Correction by Matching Prediction Distributions
We present a novel adversarial detection and correction method for machine learning classifiers.The detector consists of an autoencoder trained with a custom loss function based on the Kullback-Leibler divergence between…
PredictionEnhancing Quantum Adversarial Robustness by Randomized Encodings
The interplay between quantum physics and machine learning gives rise to the emergent frontier of quantum machine learning, where advanced quantum learning models may outperform their classical counterparts in solving ce…
Adversarial RobustnessQuantum Machine LearningLinear system security -- detection and correction of adversarial attacks in the noise-free case
We address the problem of attack detection and attack correction for multi-output discrete-time linear time-invariant systems under sensor attack. More specifically, we focus on the situation where adversarial attack sig…
Adversarial AttackFACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples
In strong adversarial attacks against deep neural networks (DNN), the generated adversarial example will mislead the DNN-implemented classifier by destroying the output features of the last layer. To enhance the robustne…
AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation
This paper describes a simple yet effective technique for refining a pretrained classifier network. The proposed AdCorDA method is based on modification of the training set and making use of the duality between network w…
Domain Adaptation