Generating Adversarial Examples with an Optimized Quality
Deep learning models are widely used in a range of application areas, such as computer vision, computer security, etc. However, deep learning models are vulnerable to Adversarial Examples (AEs),carefully crafted samples to deceive those models. Recent studies have introduced new adversarial attack methods, but, to the best of our knowledge, none provided guaranteed quality for the crafted examples as part of their creation, beyond simple quality measures such as Misclassification Rate (MR). In this paper, we incorporateImage Quality Assessment (IQA) metrics into the design and generation process of AEs. We propose an evolutionary-based single- and multi-objective optimization approaches that generate AEs with high misclassification rate and explicitly improve the quality, thus indistinguishability, of the samples, while perturbing only a limited number of pixels. In particular, several IQA metrics, including edge analysis, Fourier analysis, and feature descriptors, are leveraged into the process of generating AEs. Unique characteristics of the evolutionary-based algorithm enable us to simultaneously optimize the misclassification rate and the IQA metrics of the AEs. In order to evaluate the performance of the proposed method, we conduct intensive experiments on different well-known benchmark datasets(MNIST, CIFAR, GTSRB, and Open Image Dataset V5), while considering various objective optimization configurations. The results obtained from our experiments, when compared with the exist-ing attack methods, validate our initial hypothesis that the use ofIQA metrics within generation process of AEs can substantially improve their quality, while maintaining high misclassification rate.Finally, transferability and human perception studies are provided, demonstrating acceptable performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackComputer SecuritySimilar Papers 제목 키워드 기반
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass …
Adversarial AttackAdversarial DefenseAttacking the Madry Defense Model with $L_1$-based Adversarial Examples
The Madry Lab recently hosted a competition designed to test the robustness of their adversarially trained MNIST model. Attacks were constrained to perturb each pixel of the input image by a scaled maximal $L_\infty$ dis…
R&R: Metric-guided Adversarial Sentence Generation
Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences t…
Adversarial AttackGeneral ClassificationSemantic SimilaritySemantic Textual Similarity+4Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process
Recent research has revealed that natural language processing (NLP) models are vulnerable to adversarial examples. However, the current techniques for generating such examples rely on deterministic heuristic rules, which…
Adversarial TextSentenceNot All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target clas…
All