arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00663cs.CV
收藏

面向对抗攻击的车道线检测模型无关防御

Model-Agnostic Defense for Lane Detection against Adversarial Attack

University of California, Berkeley(加州大学伯克利分校)

Henry Xu, An Ju, David Wagner

摘要:

神经网络对对抗攻击的敏感性引发了车道检测工作的严重安全问题,这是此类模型已广泛应用的领域。最近的工作对抗道路补丁已经成功地诱导感知车道线与任意形式,提出了一种途径流氓控制车辆的行为。在本文中,我们提出了一种模块化的车道验证系统,可以在自动驾驶系统被误导之前捕获此类威胁,同时保持对特定车道检测模型的不可知性。我们的实验表明,使用简单的卷积神经网络(CNN)实现该系统可以抵御对车道检测模型的各种攻击。在对推理时间有10%影响的情况下,我们可以检测到96%的有界非自适应攻击,90%的有界自适应攻击和98%的补丁攻击,同时保留至少95%的真实车道的准确识别,这表明我们提出的验证系统可以有效地以最小的开销减轻车道检测的安全风险。

英文摘要:

Susceptibility of neural networks to adversarial attack prompts serious safety concerns for lane detection efforts, a domain where such models have been widely applied. Recent work on adversarial road patches have successfully induced perception of lane lines with arbitrary form, presenting an avenue for rogue control of vehicle behavior. In this paper, we propose a modular lane verification system that can catch such threats before the autonomous driving system is misled while remaining agnostic to the particular lane detection model. Our experiments show that implementing the system with a simple convolutional neural network (CNN) can defend against a wide gamut of attacks on lane detection models. With a 10% impact to inference time, we can detect 96% of bounded non-adaptive attacks, 90% of bounded adaptive attacks, and 98% of patch attacks while preserving accurate identification at least 95% of true lanes, indicating that our proposed verification system is effective at mitigating lane detection security risks with minimal overhead.

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。

↑