# LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications

arXiv: https://arxiv.org/abs/1910.08536 · HTML: https://mlsanity.com/paper/1910.08536/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2019.

## Built on by (most cited first, 15 of 15)

- [Jedi: Entropy-based Localization and Removal of Adversarial Patches](https://mlsanity.com/paper/2304.10029/) (2023)
- [On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving](https://mlsanity.com/paper/2201.01850/) (2022)
- [ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers](https://mlsanity.com/paper/2110.14120/) (2021)
- [Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks](https://mlsanity.com/paper/2108.05075/) (2021)
- [Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis](https://mlsanity.com/paper/2203.07341/) (2022)
- [CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models](https://mlsanity.com/paper/2206.04365/) (2022)
- [Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey](https://mlsanity.com/paper/2404.05219/) (2024)
- [SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2103.10651/) (2021)
- [FIMBA: Evaluating the Robustness of AI in Genomics via Feature Importance Adversarial Attacks](https://mlsanity.com/paper/2401.10657/) (2024)
- [Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks](https://mlsanity.com/paper/2208.09195/) (2022)
- [Defenses Against Multi-Sticker Physical Domain Attacks on Classifiers](https://mlsanity.com/paper/2101.11060/) (2021)
- [Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer](https://mlsanity.com/paper/2303.10291/) (2023)
- [EdgeShield: A Universal and Efficient Edge Computing Framework for Robust AI](https://mlsanity.com/paper/2408.04181/) (2024)
- [SoK: A Study of the Security on Voice Processing Systems](https://mlsanity.com/paper/2112.13144/) (2021)
- [Mobile Edge Adversarial Detection for Digital Twinning to the Metaverse with Deep Reinforcement Learning](https://mlsanity.com/paper/2303.10288/) (2023)

## Abstract (arXiv)

Recently, adversarial attacks can be applied to the physical world, causing practical issues to various Convolutional Neural Networks (CNNs) powered applications. Most existing physical adversarial attack defense works only focus on eliminating explicit perturbation patterns from inputs, ignoring interpretation to CNN's intrinsic vulnerability. Therefore, they lack the expected versatility to different attacks and thereby depend on considerable data processing costs. In this paper, we propose LanCe -- a comprehensive and lightweight CNN defense methodology against different physical adversarial attacks. By interpreting CNN's vulnerability, we find that non-semantic adversarial perturbations can activate CNN with significantly abnormal activations and even overwhelm other semantic input patterns' activations. We improve the CNN recognition process by adding a self-verification stage to detect the potential adversarial input with only one CNN inference cost. Based on the detection result, we further propose a data recovery methodology to defend the physical adversarial attacks. We apply such defense methodology into both image and audio CNN recognition scenarios and analyze the computational complexity for each scenario, respectively. Experiments show that our methodology can achieve an average 91% successful rate for attack detection and 89% accuracy recovery. Moreover, it is at most 3x faster compared with the state-of-the-art defense methods, making it feasible to resource-constrained embedded systems, such as mobile devices.