paper-with-me

Papers

Autoencoder-based Denoising Defense against Adversarial Attacks on Object Detection

2025-12-18 · Min Geun Song, Gang Min Kim, Woonmin Kim, Yongsik Kim, Jeonghyun Sim, Sangbeom Park, Huy Kang Kim arxiv

Deep learning-based object detection models play a critical role in real-world applications such as autonomous driving and security surveillance systems, yet they remain vulnerable to adversarial examples. In this work, we propose an autoencoder-based denoising defense to recover object detection performance degraded by adversarial perturbations. We conduct adversarial attacks using Perlin noise on vehicle-related images from the COCO dataset, apply a single-layer convolutional autoencoder to remove the perturbations, and evaluate detection performance using YOLOv5. Our experiments demonstrate that adversarial attacks reduce bbox mAP from 0.2890 to 0.1640, representing a 43.3% performance degradation. After applying the proposed autoencoder defense, bbox mAP improves to 0.1700 (3.7% recovery) and bbox mAP@50 increases from 0.2780 to 0.3080 (10.8% improvement). These results indicate that autoencoder-based denoising can provide partial defense against adversarial attacks without requiring model retraining.

📄 PDF Abstract BibTeX arXiv:2512.16123

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingObject Detection

Similar Papers 제목 키워드 기반

Frequency Centric Defense Mechanisms against Adversarial Examples

2021-10-26 · Sanket B. Shah, Param Raval, Harin Khakhi, Mehul S. Raval

Adversarial example (AE) aims at fooling a Convolution Neural Network by introducing small perturbations in the input image.The proposed work uses the magnitude and phase of the Fourier Spectrum and the entropy of the im…

Denoising

A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks

2019-06-13 · Rajeev Sahay, Rehana Mahfuz, Aly El Gamal

The reliance on deep learning algorithms has grown significantly in recent years. Yet, these models are highly vulnerable to adversarial attacks, which introduce visually imperceptible perturbations into testing data to …

Adversarial AttackDeep LearningDenoisingDimensionality Reduction

Revisiting Role of Autoencoders in Adversarial Settings

2020-05-21 · Byeong Cheon Kim, Jung Uk Kim, Hakmin Lee, Yong Man Ro

To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through …

Adversarial DefenseAdversarial RobustnessDenoising

Mitigating Gradient-based Adversarial Attacks via Denoising and Compression

2021-04-03 · Rehana Mahfuz, Rajeev Sahay, Aly El Gamal

Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network, and the risk they introduce cannot be as…

DenoisingDimensionality Reduction

Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm

2023-03-28 · Bakary Badjie, José Cecílio, António Casimiro

Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with t…

Adversarial RobustnessData PoisoningDenoising