Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018/01/02 by Naveed Akhtar, Ajmal Mian, Akhtar, Naveed +1 · 28 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Integrated Circuits and Semiconductor Failure Analysis

paper · pdf · doi:10.48550/arxiv.1801.00553

openalex publication_date 2018/01/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep learning is at the heart of the current rise of machine learning and artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, we draw on the literature to provide a broader outlook of the research direction.

Citations

• Backpropagation Applied to Handwritten Zip Code Recognition
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
• Adversarial Manipulation of Deep Representations
• Densely Connected Convolutional Networks
• Adversarial Training Methods for Semi-Supervised Text Classification
• On the (Statistical) Detection of Adversarial Examples
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
• Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
• Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Adversarial Attacks Beyond the Image Space
• Provably Minimally-Distorted Adversarial Examples
• Adversarial Examples for Semantic Segmentation and Object Detection
• Improving the Robustness of Deep Neural Networks via Stability Training
• Improving the Adversarial Robustness and Interpretability of Deep Neural\n Networks by Regularizing their Input Gradients
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
• Robustness of LLM-enabled vehicle trajectory prediction under data security threats
• A Brief Survey on Autonomous Vehicle Possible Attacks, Exploits and Vulnerabilities
• Attacking Vision-based Perception in End-to-End Autonomous Driving Models
• Transferable Adversarial Attacks for Image and Video Object Detection
• A New Type of Adversarial Examples
• StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
• Restricted Receptive Fields for Face Verification
• Visualizing Representations of Adversarially Perturbed Inputs
• Deep Learning-Based Multi-Factor Authentication: A Survey of Biometric and Smart Card Integration Approaches
• Understanding Measures of Uncertainty for Adversarial Example Detection
• Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
• An Empirical Review of Adversarial Defenses
• Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
• StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models
• Hardware Trojan Attacks on Neural Networks
• Secure human oversight of AI: Threat modeling in a socio-technical context
• Robustness of Rotation-Equivariant Networks to Adversarial Perturbations
• Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
• Adversarial Attacks on Cognitive Self-Organizing Networks: The Challenge\n and the Way Forward
• Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness
• SeDA: Secure and Efficient DNN Accelerators with Hardware/Software Synergy
• Neural Style Transfer: A Review
• Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches
• A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
• Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
• Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN
• Understanding the Risks of Asphalt Art on the Reliability of Surveillance Perception Systems
• Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense

Related

• Advances in adversarial attacks and defenses in computer vision: A\n survey
• A Review of Adversarial Attacks in Computer Vision
• A Survey on Physical Adversarial Attack in Computer Vision
• A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges
• Visual Adversarial Attacks and Defenses in the Physical World: A Survey