# Local Gradients Smoothing: Defense against localized adversarial attacks

arXiv: https://arxiv.org/abs/1807.01216 · HTML: https://mlsanity.com/paper/1807.01216/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

## Built on by (most cited first, 30 of 87)

- [Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection](https://mlsanity.com/paper/2112.04532/) (2021)
- [On Generating Transferable Targeted Perturbations](https://mlsanity.com/paper/2103.14641/) (2021)
- [PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier](https://mlsanity.com/paper/2108.09135/) (2021)
- [Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them](https://mlsanity.com/paper/2107.11630/) (2021)
- [Certified Patch Robustness via Smoothed Vision Transformers](https://mlsanity.com/paper/2110.07719/) (2021)
- [Towards Practical Certifiable Patch Defense with Vision Transformer](https://mlsanity.com/paper/2203.08519/) (2022)
- [Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks](https://mlsanity.com/paper/2212.12995/) (2022)
- [TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems](https://mlsanity.com/paper/2111.09999/) (2021)
- [Jedi: Entropy-based Localization and Removal of Adversarial Patches](https://mlsanity.com/paper/2304.10029/) (2023)
- [PAD: Patch-Agnostic Defense against Adversarial Patch Attacks](https://mlsanity.com/paper/2404.16452/) (2024)
- [PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch](https://mlsanity.com/paper/2207.01795/) (2022)
- [DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks](https://mlsanity.com/paper/2102.02956/) (2021)
- [PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches](https://mlsanity.com/paper/2104.12609/) (2021)
- [Efficient Certified Defenses Against Patch Attacks on Image Classifiers](https://mlsanity.com/paper/2102.04154/) (2021)
- [ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking](https://mlsanity.com/paper/2202.01811/) (2022)
- [Efficient Decision-based Black-box Patch Attacks on Video Recognition](https://mlsanity.com/paper/2303.11917/) (2023)
- [Generative Dynamic Patch Attack](https://mlsanity.com/paper/2111.04266/) (2021)
- [Query-Efficient Decision-based Black-Box Patch Attack](https://mlsanity.com/paper/2307.00477/) (2023)
- [REAP: A Large-Scale Realistic Adversarial Patch Benchmark](https://mlsanity.com/paper/2212.05680/) (2022)
- [Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches](https://mlsanity.com/paper/2103.08860/) (2021)
- [Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey](https://mlsanity.com/paper/2206.08304/) (2022)
- [Attacking Video Recognition Models with Bullet-Screen Comments](https://mlsanity.com/paper/2110.15629/) (2021)
- [Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation](https://mlsanity.com/paper/2209.05980/) (2022)
- [ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers](https://mlsanity.com/paper/2110.14120/) (2021)
- [DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks](https://mlsanity.com/paper/2306.09124/) (2023)
- [Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks](https://mlsanity.com/paper/2108.05075/) (2021)
- [PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing](https://mlsanity.com/paper/2111.10481/) (2021)
- [Visual Adversarial Attacks and Defenses in the Physical World: A Survey](https://mlsanity.com/paper/2211.01671/) (2022)
- [PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses](https://mlsanity.com/paper/2310.13076/) (2023)
- [Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis](https://mlsanity.com/paper/2203.07341/) (2022)

## Abstract (arXiv)

Deep neural networks (DNNs) have shown vulnerability to adversarial attacks, i.e., carefully perturbed inputs designed to mislead the network at inference time. Recently introduced localized attacks, Localized and Visible Adversarial Noise (LaVAN) and Adversarial patch, pose a new challenge to deep learning security by adding adversarial noise only within a specific region without affecting the salient objects in an image. Driven by the observation that such attacks introduce concentrated high-frequency changes at a particular image location, we have developed an effective method to estimate noise location in gradient domain and transform those high activation regions caused by adversarial noise in image domain while having minimal effect on the salient object that is important for correct classification. Our proposed Local Gradients Smoothing (LGS) scheme achieves this by regularizing gradients in the estimated noisy region before feeding the image to DNN for inference. We have shown the effectiveness of our method in comparison to other defense methods including Digital Watermarking, JPEG compression, Total Variance Minimization (TVM) and Feature squeezing on ImageNet dataset. In addition, we systematically study the robustness of the proposed defense mechanism against Back Pass Differentiable Approximation (BPDA), a state of the art attack recently developed to break defenses that transform an input sample to minimize the adversarial effect. Compared to other defense mechanisms, LGS is by far the most resistant to BPDA in localized adversarial attack setting.