# A study of the effect of JPG compression on adversarial images

arXiv: https://arxiv.org/abs/1608.00853 · HTML: https://mlsanity.com/paper/1608.00853/

## Key facts

- Cited by 197 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2016.

## Built on by (most cited first, 30 of 197)

- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [Frequency Domain Model Augmentation for Adversarial Attack](https://mlsanity.com/paper/2207.05382/) (2022)
- [Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks](https://mlsanity.com/paper/2106.09249/) (2021)
- [Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics](https://mlsanity.com/paper/2411.13587/) (2024)
- [SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)](https://mlsanity.com/paper/2108.04974/) (2021)
- [Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection](https://mlsanity.com/paper/2112.04532/) (2021)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches](https://mlsanity.com/paper/2207.04718/) (2022)
- [AdvDrop: Adversarial Attack to DNNs by Dropping Information](https://mlsanity.com/paper/2108.09034/) (2021)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Meta Gradient Adversarial Attack](https://mlsanity.com/paper/2108.04204/) (2021)
- [Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving](https://mlsanity.com/paper/2101.06784/) (2021)
- [Reveal of Vision Transformers Robustness against Adversarial Attacks](https://mlsanity.com/paper/2106.03734/) (2021)
- [A Comprehensive Evaluation Framework for Deep Model Robustness](https://mlsanity.com/paper/2101.09617/) (2021)
- [Sparsity Winning Twice: Better Robust Generalization from More Efficient Training](https://mlsanity.com/paper/2202.09844/) (2022)
- [One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models](https://mlsanity.com/paper/2406.05491/) (2024)
- [Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression](https://mlsanity.com/paper/2301.13838/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models](https://mlsanity.com/paper/2404.10335/) (2024)
- [DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection](https://mlsanity.com/paper/2305.13625/) (2023)
- [DISCO: Adversarial Defense with Local Implicit Functions](https://mlsanity.com/paper/2212.05630/) (2022)
- [Robustness of SAM: Segment Anything Under Corruptions and Beyond](https://mlsanity.com/paper/2306.07713/) (2023)
- [PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch](https://mlsanity.com/paper/2207.01795/) (2022)
- [JEM++: Improved Techniques for Training JEM](https://mlsanity.com/paper/2109.09032/) (2021)
- [A Frequency Perspective of Adversarial Robustness](https://mlsanity.com/paper/2111.00861/) (2021)
- [Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective](https://mlsanity.com/paper/2404.19287/) (2024)
- [EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models](https://mlsanity.com/paper/2311.12066/) (2023)
- [Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning](https://mlsanity.com/paper/2112.08691/) (2021)
- [A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks](https://mlsanity.com/paper/2212.10230/) (2022)
- [TPatch: A Triggered Physical Adversarial Patch](https://mlsanity.com/paper/2401.00148/) (2023)

## Abstract (arXiv)

Neural network image classifiers are known to be vulnerable to adversarial images, i.e., natural images which have been modified by an adversarial perturbation specifically designed to be imperceptible to humans yet fool the classifier. Not only can adversarial images be generated easily, but these images will often be adversarial for networks trained on disjoint subsets of data or with different architectures. Adversarial images represent a potential security risk as well as a serious machine learning challenge---it is clear that vulnerable neural networks perceive images very differently from humans. Noting that virtually every image classification data set is composed of JPG images, we evaluate the effect of JPG compression on the classification of adversarial images. For Fast-Gradient-Sign perturbations of small magnitude, we found that JPG compression often reverses the drop in classification accuracy to a large extent, but not always. As the magnitude of the perturbations increases, JPG recompression alone is insufficient to reverse the effect.