Skip to content
Log in
Review Open access

A Survey on Adversarial Deep Learning in Computer Vision

Maisam Abbas Ran-Zan Wang
2026 · IEEE Open Journal of the Computer Society · Vol 7, pp. 1344-1363 · 0 citations · 116 references

TL;DR

This paper advocates for a forward-thinking approach that balances technical sophistication with human-centric principles, ensuring that adversarial deep learning evolves into a discipline not just of technical defense, but also of trust, transparency, and accountability.

Abstract

Adversarial deep learning has emerged as a critical area of research within computer vision, revealing both the vulnerabilities and resilience of modern neural networks. This study provides a comprehensive survey of adversarial attacks and corresponding defense mechanisms, bridging foundational concepts with recent advancements. The taxonomy of adversarial attacks is thoroughly examined, including white-box, limited-information, real-world, and modern attacks, each exploiting specific vulnerabilities in deep learning models. On the defense front, this paper explores an extensive range of strategies, from adversarial training and architectural modifications to certifiable robustness frameworks and semantic-level defenses, emphasizing their strengths and limitations. Despite significant progress, the dynamic and evolving nature of adversarial threats underscores the need for adaptive, human-centered solutions. Integrating robust defenses such as input reconstruction, ensemble-based models, and dynamic mechanisms highlights the field’s innovation, but challenges persist in achieving universal robustness and scalability. This survey emphasizes the importance of interdisciplinary collaboration, blending human perception, computational security, and explainable AI to design defenses that align with real-world complexities and ethical considerations. By critically analyzing current methodologies and proposing future directions, this paper contributes to advancing the security and reliability of computer vision applications. It advocates for a forward-thinking approach that balances technical sophistication with human-centric principles, ensuring that adversarial deep learning evolves into a discipline not just of technical defense, but also of trust, transparency, and accountability.

DOI Semantic Scholar
Read PDF

Similar papers

Review Aug 2026

A Comprehensive Review on Adversarial Attacks and Detection Techniques in Deep Learning Models for Image Analysis

The research methodology involved a systematic literature review using the Scopus database, adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, and focusing on recent advancements in attack and defence techniques.

Reeti Jaswal, Vikas Khullar, Surya Narayan Panda · 0 citations
Review Open access Jul 2026

A Comprehensive Survey of Adversarial Attacks and Defense Strategies in Artificial Intelligence Security

This survey provides a comprehensive synthesis of adversarial attacks and defense mechanisms in modern AI security, introducing a structured taxonomy categorizing attacks into evasion, poisoning, and model inversion strategies, evaluated across varying levels of attacker knowledge.

P. Mahalakshmi, D. Jayalakshmi · 0 citations
Open access Jul 2026

Comparative Analysis of Adversarial Robustness Across CNN, VGG19, and Vision Transformer Architectures Using Multiple Defense Strategies

The study concluded that adversarial resilience is largely determined by the interaction between model architecture and defense strategy, highlighting the need for architecture-specific defense selection when developing secure medical image classification systems.

Y. Heryadi, I. Sonata, Bambang Krismono Triwijoyo · 0 citations
Aug 2026

Enhancing robustness of deep learning-based malware detection against adversarial attacks

This paper introduces DefendMal, a novel framework that synergistically combines Denoise Autoencoder with Sequence Squeezing, a Context-aware Adversarial Generator (CAG-AdvGAN), Projected Gradient Descent (PGD) adversarial training, and a Positive–Negative Detector with Variational Autoencoder (PNDetector-VAE) to enhance robustness against evolving adversarial threats.

Dennis Benedict Crasta, Vikash Kumar · 0 citations
Open access 2026

Adversarial Training Foundations: Methods to Enhance Neural Network Robustness

The study systematically compares two distinct adversarial training strategies: ‘pre-train’, where adversarial examples are generated beforehand, and ‘in-train’, where perturbations are introduced dynamically during the training process, to understand the advantages and limitations of each approach in enhancing model robustness.

José María Jorquera Valero, Ibon Bengoechea Cazorla, Manuel Gil Pérez · 0 citations
Open access Aug 2026

Enhanced Robustness in Neural Network Models against Adversarial Attacks and their Performance Analysis

Machine learning models, particularly deep learning architectures, achieve high performance in prediction tasks but remain susceptible to adversarial attacks. This study aims to enhance the robustness of Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), and Recurrent Neural Networks (RNNs), thereby improving the security of machine learning systems. A three-step approach is adopted. First, benign sample classification is performed using the MNIST benchmark dataset. Second, adversarial attacks, namely Projected Gradient Descent (PGD), DeepFool (DF), and the Fast Gradient Sign Method (FGSM), are launched on the trained models, resulting in significant performance degradation. Based on the biased outputs induced by adversarial perturbations, an adversarial detection model is subsequently established. Third, to counteract these attacks, various defense strategies, including adversarial training, defensive distillation, autoencoder-based denoising, ensemble methods, and feature squeezing are employed and evaluated using standard performance metrics and graphical analyses. The results indicate that, in the absence of defense mechanisms, PGD attacks lead to accuracy drops of approximately 27% in CNNs, 83% in DNNs, and 90% in RNNs, demonstrating severe model vulnerabilities. However, when defense strategies are applied, all models recover to an accuracy of at least 98.9%, with adversarial training improving performance under attack by up to 90%. Among the evaluated models, CNNs exhibit the highest baseline robustness, whereas DNNs and RNNs rely more heavily on defense mechanisms to maintain performance. These findings provide valuable insights into the development of secure and resilient machine learning systems capable of mitigating adversarial threats.

Surekha M., A. K. Sagar, Vineeta Khemchandani · 0 citations