A Survey of Black-Box Adversarial Attacks on Computer Vision Models

Abstract

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life scenarios, pose a severe challenge to their applicability, pushing research into the direction which aims to enhance the robustness of these models. After the introduction of these perturbations by Szegedy et al. [1], significant amount of research has focused on the reliability of such models, primarily in two aspects - white-box, where the adversary has access to the targeted model and related parameters; and the black-box, which resembles a real-life scenario with the adversary having almost no knowledge of the model to be attacked. To provide a comprehensive security cover, it is essential to identify, study, and build defenses against such attacks. Hence, in this paper, we propose to present a comprehensive comparative study of various black-box adversarial attacks and defense techniques.

arXiv comment33 pages

References in corpus (25)

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• Conditional Image Generation with PixelCNN Decoders
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Certified Adversarial Robustness via Randomized Smoothing
• Countering Adversarial Images using Input Transformations
• Adversarial Machine Learning at Scale
• Black-box Adversarial Attacks with Limited Queries and Information
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• A study of the effect of JPG compression on adversarial images
• Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
• Motivating the Rules of the Game for Adversarial Example Research
• Simple Black-box Adversarial Attacks
• DeepFool: a simple and accurate method to fool deep neural networks
• Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks
• Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
• POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm
• Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
• Defending against Adversarial Images using Basis Functions Transformations
• AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks
• A Survey on Resilient Machine Learning
• Curls & Whey: Boosting Black-Box Adversarial Attacks

Cited by in corpus (8)

• AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
• Adversarial Machine Learning in Wireless Communications using RF Data: A Review
• Adversarial Example Games
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Frequency-Tuned Universal Adversarial Attacks
• Distributionally Robust Multi-Output Regression Ranking
• Do Deep Minds Think Alike? Selective Adversarial Attacks for Fine-Grained Manipulation of Multiple Deep Neural Networks
• Orthogonal Deep Models As Defense Against Black-Box Attacks