A Survey of Black-Box Adversarial Attacks on Computer Vision Models
arXiv:1912.01667
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.
33 pages
References in corpus (10)
- Distilling the Knowledge in a Neural Network
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Certified Adversarial Robustness via Randomized Smoothing
- Countering Adversarial Images using Input Transformations
- Adversarial Machine Learning at Scale
- A study of the effect of JPG compression on adversarial images
- Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
- POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm
- A Survey on Resilient Machine Learning
- Curls & Whey: Boosting Black-Box Adversarial Attacks