# Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving Source: [Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:43:15.362Z Authors: Ibrahim Sobh, Ahmed Hamed, Varun Ravi Kumar, Senthil Yogamani Published: 2021-07-15T16:53:48.000Z ## Abstract Deep neural networks (DNNs) have accomplished impressive success in various applications, including autonomous driving perception tasks, in recent years. On the other hand, current deep neural networks are easily fooled by adversarial attacks. This vulnerability raises significant concerns, particularly in safety-critical applications. As a result, research into attacking and defending DNNs has gained much coverage. In this work, detailed adversarial attacks are applied on a diverse multi-task visual perception deep network across distance estimation, semantic segmentation, motion detection, and object detection. The experiments consider both white and black box attacks for targeted and un-targeted cases, while attacking a task and inspecting the effect on all the others, in addition to inspecting the effect of applying a simple defense method. We conclude this paper by comparing and discussing the experimental results, proposing insights and future work. The visualizations of the attacks are available at https://youtu.be/6AixN90budY. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()