# Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving

arXiv: https://arxiv.org/abs/2107.07449 · HTML: https://mlsanity.com/paper/2107.07449/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 15 Jul 2021.

## Builds on (most cited first, 26 of 26)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [Fooling automated surveillance cameras: adversarial patches to attack person detection](https://mlsanity.com/paper/1904.08653/) (2019)
- [A study of the effect of JPG compression on adversarial images](https://mlsanity.com/paper/1608.00853/) (2016)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Adversarial Objects Against LiDAR-Based Autonomous Driving Systems](https://mlsanity.com/paper/1907.05418/) (2019)
- [OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving](https://mlsanity.com/paper/2102.07448/) (2021)
- [SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2008.04017/) (2020)
- [MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning](https://mlsanity.com/paper/1904.08492/) (2019)
- [Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline](https://mlsanity.com/paper/2012.02124/) (2020)
- [FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Driving](https://mlsanity.com/paper/1910.04076/) (2019)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems](https://mlsanity.com/paper/2001.02223/) (2020)
- [UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Models](https://mlsanity.com/paper/2007.06676/) (2020)
- [SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras](https://mlsanity.com/paper/2104.04420/) (2021)
- [Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learning](https://mlsanity.com/paper/2104.14042/) (2021)
- [Monocular Fisheye Camera Depth Estimation Using Sparse LiDAR Supervision](https://mlsanity.com/paper/1803.06192/) (2018)
- [AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving](https://mlsanity.com/paper/1901.05808/) (2019)
- [FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving](https://mlsanity.com/paper/1908.11789/) (2019)
- [TiledSoilingNet: Tile-level Soiling Detection on Automotive Surround-view Cameras Using Coverage Metric](https://mlsanity.com/paper/2007.00801/) (2020)
- [Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving](https://mlsanity.com/paper/1901.03912/) (2019)
- [NeurAll: Towards a Unified Visual Perception Model for Automated Driving](https://mlsanity.com/paper/1902.03589/) (2019)
- [An Online Learning System for Wireless Charging Alignment using Surround-view Fisheye Cameras](https://mlsanity.com/paper/2105.12763/) (2021)

## Built on by (most cited first, 14 of 14)

- [Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges](https://mlsanity.com/paper/2205.13281/) (2022)
- [SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving](https://mlsanity.com/paper/2203.05056/) (2022)
- [LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation](https://mlsanity.com/paper/2111.04875/) (2021)
- [Detecting Adversarial Perturbations in Multi-Task Perception](https://mlsanity.com/paper/2203.01177/) (2022)
- [Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge](https://mlsanity.com/paper/2409.01627/) (2024)
- [Woodscape Fisheye Object Detection for Autonomous Driving -- CVPR 2022 OmniCV Workshop Challenge](https://mlsanity.com/paper/2206.12912/) (2022)
- [Adversarial Attacks on Hidden Tasks in Multi-Task Learning](https://mlsanity.com/paper/2405.15244/) (2024)
- [SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving](https://mlsanity.com/paper/2206.02876/) (2022)
- [Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning](https://mlsanity.com/paper/2305.12066/) (2023)
- [Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries](https://mlsanity.com/paper/2508.10039/) (2025)
- [RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather](https://mlsanity.com/paper/2112.02469/) (2021)
- [WoodScape Motion Segmentation for Autonomous Driving -- CVPR 2023 OmniCV Workshop Challenge](https://mlsanity.com/paper/2401.00910/) (2023)
- [Multi-Modal Traffic Sign Detection with Semantic Attributes for Autonomous Driving](https://mlsanity.com/paper/2608.20874/) (2026)
- [MotionSync: Non-Causal Refinement of Causal Tracker for Label-Efficient 3D Perception](https://mlsanity.com/paper/2608.29567/) (2026)

## Abstract (arXiv)

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.