基于注意力的视觉应用中物理对抗攻击的实时防御
Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications
AI总结：
针对视觉应用中物理对抗攻击的实时防御难题，本文提出基于对抗通道注意力的高效多帧防御机制，在浅层网络快速识别并掩盖恶意对象，兼顾防御性能与计算成本。
摘要：
深度神经网络在计算机视觉任务中表现出优异的性能，但其易受通过物理对象实现的真实世界对抗攻击的影响，这些攻击能够破坏其预测，从而对其在安全关键领域的应用构成严重的安全隐患。现有防御方法侧重于单帧分析，且具有高计算成本的特点，这限制了它们在多帧场景中的适用性，而在这些场景中实时决策至关重要。为解决这一问题，本文提出了一种高效的基于注意力的防御机制，该机制利用对抗通道注意力在浅层网络层中快速识别和跟踪恶意对象，并在多帧设置中掩盖其对抗效应。这项工作通过增强现有的针对真实世界对抗攻击的过度激活技术，使其可用于实时应用，从而推进了现有技术水平。它还引入了一个高效的多帧防御框架，并通过旨在评估防御性能和计算成本的广泛实验验证了其有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
