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

2019/12/03 by Siddhant Bhambri, Sumanyu Muku, Bhambri, Siddhant +5 · 3 citations
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Physical Unclonable Functions (PUFs) and Hardware Security

paper · pdf · doi:10.48550/arxiv.1912.01667

openalex publication_date 2019/12/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• Gradient-based learning applied to document recognition
• A study of the effect of JPG compression on adversarial images
• Adversarial Machine Learning at Scale
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
• Countering Adversarial Images using Input Transformations
• Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
• Motivating the Rules of the Game for Adversarial Example Research
• Certified Adversarial Robustness via Randomized Smoothing
• DeepFool: a simple and accurate method to fool deep neural networks
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications
• NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Conditional Image Generation with PixelCNN Decoders
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Exposing Vulnerabilities in Counterfeit Prevention Systems Utilizing Physically Unclonable Surface Features
• Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
• Adversarial Attacks against Neural Ranking Models via In-Context Learning

Related

• A Review of Adversarial Attacks in Computer Vision
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
• A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges
• Advances in adversarial attacks and defenses in computer vision: A\n survey