# Deflecting Adversarial Attacks with Pixel Deflection

arXiv: https://arxiv.org/abs/1801.08926 · HTML: https://mlsanity.com/paper/1801.08926/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2018.

## Built on by (most cited first, 30 of 71)

- [AdvDrop: Adversarial Attack to DNNs by Dropping Information](https://mlsanity.com/paper/2108.09034/) (2021)
- [Adversarial Example Detection for DNN Models: A Review and Experimental Comparison](https://mlsanity.com/paper/2105.00203/) (2021)
- [DISCO: Adversarial Defense with Local Implicit Functions](https://mlsanity.com/paper/2212.05630/) (2022)
- [Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems](https://mlsanity.com/paper/2201.06192/) (2022)
- [RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World](https://mlsanity.com/paper/2307.07653/) (2023)
- [Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks](https://mlsanity.com/paper/2205.12134/) (2022)
- [MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes](https://mlsanity.com/paper/2103.14211/) (2021)
- [Attack to Fool and Explain Deep Networks](https://mlsanity.com/paper/2106.10606/) (2021)
- [Stereoscopic Universal Perturbations across Different Architectures and Datasets](https://mlsanity.com/paper/2112.06116/) (2021)
- [Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting](https://mlsanity.com/paper/2101.11466/) (2021)
- [Towards Good Practices in Evaluating Transfer Adversarial Attacks](https://mlsanity.com/paper/2211.09565/) (2022)
- [Local Competition and Stochasticity for Adversarial Robustness in Deep Learning](https://mlsanity.com/paper/2101.01121/) (2021)
- [Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling](https://mlsanity.com/paper/2205.14283/) (2022)
- [Understanding Adversarial Robustness Against On-manifold Adversarial Examples](https://mlsanity.com/paper/2210.00430/) (2022)
- [Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models](https://mlsanity.com/paper/2310.07492/) (2023)
- [Robust Real-World Image Super-Resolution against Adversarial Attacks](https://mlsanity.com/paper/2208.00428/) (2022)
- [Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2](https://mlsanity.com/paper/2510.24195/) (2025)
- [Enhancing Adversarial Robustness for Deep Metric Learning](https://mlsanity.com/paper/2203.01439/) (2022)
- [Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation](https://mlsanity.com/paper/2504.14541/) (2025)
- [Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection](https://mlsanity.com/paper/2103.05354/) (2021)
- [Sub-token ViT Embedding via Stochastic Resonance Transformers](https://mlsanity.com/paper/2310.03967/) (2023)
- [Adversarial Attack and Defense in Deep Ranking](https://mlsanity.com/paper/2106.03614/) (2021)
- [Improving Black-box Robustness with In-Context Rewriting](https://mlsanity.com/paper/2402.08225/) (2024)
- [Improved Text Classification via Test-Time Augmentation](https://mlsanity.com/paper/2206.13607/) (2022)
- [Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks](https://mlsanity.com/paper/2204.12050/) (2022)
- [How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation](https://mlsanity.com/paper/2205.07874/) (2022)
- [Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks](https://mlsanity.com/paper/2210.09588/) (2022)
- [Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation](https://mlsanity.com/paper/2307.07269/) (2023)
- [Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization](https://mlsanity.com/paper/2410.03376/) (2024)
- [All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines](https://mlsanity.com/paper/2112.09219/) (2021)

## Abstract (arXiv)

CNNs are poised to become integral parts of many critical systems. Despite their robustness to natural variations, image pixel values can be manipulated, via small, carefully crafted, imperceptible perturbations, to cause a model to misclassify images. We present an algorithm to process an image so that classification accuracy is significantly preserved in the presence of such adversarial manipulations. Image classifiers tend to be robust to natural noise, and adversarial attacks tend to be agnostic to object location. These observations motivate our strategy, which leverages model robustness to defend against adversarial perturbations by forcing the image to match natural image statistics. Our algorithm locally corrupts the image by redistributing pixel values via a process we term pixel deflection. A subsequent wavelet-based denoising operation softens this corruption, as well as some of the adversarial changes. We demonstrate experimentally that the combination of these techniques enables the effective recovery of the true class, against a variety of robust attacks. Our results compare favorably with current state-of-the-art defenses, without requiring retraining or modifying the CNN.