Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingMotion Detectionobject-detectionObject DetectionSemantic SegmentationSimilar Papers 제목 키워드 기반
Can audio-visual integration strengthen robustness under multimodal attacks?
In this paper, we propose to make a systematic study on machines multisensory perception under attacks. We use the audio-visual event recognition task against multimodal adversarial attacks as a proxy to investigate the …
audio-visual learningVisual LocalizationOn the Natural Robustness of Vision-Language Models Against Visual Perception Attacks in Autonomous Driving
Autonomous vehicles (AVs) rely on deep neural networks (DNNs) for critical tasks such as traffic sign recognition (TSR), automated lane centering (ALC), and vehicle detection (VD). However, these models are vulnerable to…
Autonomous DrivingAutonomous VehiclesTraffic Sign Recognitionvehicle detectionCARNet: Collaborative Adversarial Resilience for Robust Underwater Image Enhancement and Perception
Due to the uneven absorption of different light wavelengths in aquatic environments, underwater images suffer from low visibility and clear color deviations. With the advancement of autonomous underwater vehicles, extens…
Image EnhancementAdversarial attacks hidden in plain sight
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural…
General ClassificationReinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments
Adversarial attacks in 3D environments have emerged as a critical threat to the reliability of visual perception systems, particularly in safety-sensitive applications such as identity verification and autonomous driving…
3D Object ClassificationAutonomous DrivingFace Recognition