paper-with-me

홈 › Papers

Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications

2023-11-19 · Giulio Rossolini, Alessandro Biondi, Giorgio Buttazzo

Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns for their application in safety-critical domains. Existing defense methods focus on single-frame analysis and are characterized by high computational costs that limit their applicability in multi-frame scenarios, where real-time decisions are crucial. To address this problem, this paper proposes an efficient attention-based defense mechanism that exploits adversarial channel-attention to quickly identify and track malicious objects in shallow network layers and mask their adversarial effects in a multi-frame setting. This work advances the state of the art by enhancing existing over-activation techniques for real-world adversarial attacks to make them usable in real-time applications. It also introduces an efficient multi-frame defense framework, validating its efficacy through extensive experiments aimed at evaluating both defense performance and computational cost.

📄 PDF Abstract BibTeX arXiv:2311.11191

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Visually Adversarial Attacks and Defenses in the Physical World: A Survey

2022-11-03 · Xingxing Wei, Bangzheng Pu, Jiefan Lu, Baoyuan Wu

Although Deep Neural Networks (DNNs) have been widely applied in various real-world scenarios, they are vulnerable to adversarial examples. The current adversarial attacks in computer vision can be divided into digital a…

Adversarial RobustnessSurvey

Defenses Against Multi-Sticker Physical Domain Attacks on Classifiers

2021-01-26 · Xinwei Zhao, Matthew C. Stamm

Recently, physical domain adversarial attacks have drawn significant attention from the machine learning community. One important attack proposed by Eykholt et al. can fool a classifier by placing black and white sticker…

Real-Time Detectors for Digital and Physical Adversarial Inputs to Perception Systems

2020-02-23 · Yiannis Kantaros, Taylor Carpenter, Kaustubh Sridhar, Yahan Yang 외

Deep neural network (DNN) models have proven to be vulnerable to adversarial digital and physical attacks. In this paper, we propose a novel attack- and dataset-agnostic and real-time detector for both types of adversari…

Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT

2026-07-08 · Giulia Marchiori Pietrosanti, Giulio Rossolini, Giorgio Buttazzo arxiv

Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.g., adversarial patches, while recent test-time defenses mitigate them by suppressing image tokens with abnormally high attention scores. T…

A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World

2025-10-20 · Wei Zhang, Zhanhao Hu, Xiao Li, Xiaopei Zhu 외 arxiv

In recent years, adversarial attacks against deep learning-based object detectors in the physical world have attracted much attention. To defend against these attacks, researchers have proposed various defense methods ag…

Adversarial Defense