NDSS 2025 – L-HAWK: A Controllable Physical Adversarial Patch Against A Long-Distance Target
嗯，用户让我总结一下这篇文章的内容，控制在一百个字以内。首先，我需要快速浏览文章，抓住主要信息。文章标题是“L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target”，看起来是关于自动驾驶汽车的物理对抗攻击。
作者们来自西电和北大，他们提出了一种名为L-HAWK的新方法。这种方法使用激光信号来触发攻击，只针对特定车辆，而不是所有车辆。这比现有的攻击更可控。
文章提到L-HAWK在50米外的成功率高达91.9%，比之前的TPatch在7米处的59%成功率有了显著提升。这说明L-HAWK不仅攻击距离更远，成功率也更高。
接下来，我需要将这些关键点浓缩到100字以内。要包括L-HAWK是什么、它的特点、优势以及应用场景。可能的结构是：介绍L-HAWK，说明其触发机制和目标选择，然后提到成功率和距离提升。
最后检查一下是否符合用户的要求：用中文总结，不超过100字，不需要特定开头。确保信息准确且简洁。
</think>
研究者提出了一种名为L-HAWK的可控物理对抗补丁，通过长距离激光信号触发，仅针对特定车辆实施攻击。该方法采用异步学习优化激光参数和对抗补丁，并通过多角度模拟、噪声近似和渐进采样提升攻击鲁棒性。实验显示，在50米外的成功率达91.9%，较现有方法显著提升攻击距离和成功率。
2026-3-5 20:0:0
Author: securityboulevard.com(查看原文)
阅读量:17
收藏
Session 14D: Autonomous Vehicles
Authors, Creators & Presenters: Taifeng Liu (Xidian University), Yang Liu (Xidian University), Zhuo Ma (Xidian University), Tong Yang (Peking University), Xinjing Liu (Xidian University), Teng Li (Xidian University), Jianfeng Ma (Xidian University)
PAPER
L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target
The vision-based perception modules in autonomous vehicles (AVs) are prone to physical adversarial patch attacks. However, most existing attacks indiscriminately affect all passing vehicles. This paper introduces L-HAWK, a novel controllable physical adversarial patch activated by long-distance laser signals. L-HAWK is designed to target specific vehicles when the adversarial patch is triggered by laser signals while remaining benign under normal conditions. To achieve this goal and address the unique challenges associated with laser signals, we propose an asynchronous learning method for L-HAWK to determine the optimal laser parameters and the corresponding adversarial patch. To enhance the attack robustness in real-world scenarios, we introduce a multi-angle and multi-position simulation mechanism, a noise approximation approach, and a progressive sampling-based method. L-HAWK has been validated through extensive experiments in both digital and physical environments. Compared to a 59% success rate of TPatch (USENIX ’23) at 7 meters, L-HAWK achieves a 91.9% average attack success rate at 50 meters. This represents a 56% improvement in attack success rate and a more than sevenfold increase in attack distance.
ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.
