# Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks

arXiv: https://arxiv.org/abs/2408.13274 · HTML: https://mlsanity.com/paper/2408.13274/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 18 of 18)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [On the Robustness of Large Multimodal Models Against Image Adversarial Attacks](https://mlsanity.com/paper/2312.03777/) (2023)
- [Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors](https://mlsanity.com/paper/2006.06356/) (2020)
- [Towards Robust Image Classification Using Sequential Attention Models](https://mlsanity.com/paper/1912.02184/) (2019)
- [Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and their Impact](https://mlsanity.com/paper/2307.02055/) (2023)
- [AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization](https://mlsanity.com/paper/2402.11940/) (2024)
- [TensorShield: Tensor-based Defense Against Adversarial Attacks on Images](https://mlsanity.com/paper/2002.10252/) (2020)
- [Adversarial Attacks on Image Classification Models: Analysis and Defense](https://mlsanity.com/paper/2312.16880/) (2023)

## Built on by (most cited first, 2 of 2)

- [FusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning](https://mlsanity.com/paper/2508.20817/) (2025)
- [A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures](https://mlsanity.com/paper/2602.07028/) (2026)

## Abstract (arXiv)

Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense mechanisms against these attacks to enhance the resilience of neural networks. We employ a combination of adversarial training and innovative preprocessing techniques, aiming to mitigate the impact of adversarial perturbations. Our methodology involves modifying input data before classification and investigating different model architectures and training strategies. Through rigorous evaluation of benchmark datasets, we demonstrate the effectiveness of our approach in defending against FGSM and PGD attacks. Our results show substantial improvements in model robustness compared to baseline methods, highlighting the potential of our defense strategies in real-world applications. This study contributes to the ongoing efforts to develop secure and reliable machine learning systems, offering practical insights and paving the way for future research in adversarial defense. By bridging theoretical advancements and practical implementation, we aim to enhance the trustworthiness of AI applications in safety-critical domains.