Adversarial Attacks on Autonomous Driving Perception Systems: A Multi-Sensor Perspective

📌 Overview

MSP-Attacks is a curated repository of research papers on adversarial attacks targeting autonomous driving perception systems. This project focuses on vulnerabilities across single-sensor modalities and multi-sensor fusion frameworks, aiming to provide the community with a structured reference for understanding, comparing, and tracking the latest research trends.

🎯 Research Scope

Coming soon......

Methods: A Survey

Adversarial Attacks on Object Classification

Year	Venue	Paper Title	Link
2018	CVPR	Robust Physical-World Attacks on Deep Learning Visual Classification	Code
2021	JIOT	Adaptive Square Attack: Fooling Autonomous Cars With Adversarial Traffic Signs	Code
2020	CVPR	Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles	Code
2023	T-PAMI	Adversarial Stickers: A Stealthy Attack Method in the Physical World	Code
2019	AAAI	Perceptual-Sensitive GAN for Generating Adversarial Patches	Code
2020	CVPR	PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving	Code
2021	ICCV	Naturalistic Physical Adversarial Patch for Object Detectors	Code
2019	PMLR	Adversarial camera stickers: A physical camera-based attack on deep learning systems	Code
2021	CVPR	Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink	Code
2023	PMLR	Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs	Code
2023	Computers & Security	Light can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Spot Light	Code
2022	CVPR	Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon	Code
2024	NDSS	Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception	Project Page

Adversarial Attacks on Object Classification

Year	Venue	Paper Title	Link
2017	CVPR	NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles	-

| 2021 | CVPR | Seeing isn’t Believing: Towards More Robust Adversarial Attack Against Real World Object Detectors | Project Page |

| 2020 | TPS-ISA | Adversarial Objectness Gradient Attacks in Real-time Object Detection Systems | Code |

| 2025 | ICCV | Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving | [Code][-] |

| 2025 | ICCV | Adversarial Attention Perturbations for Large Object Detection Transformers | Code |

| 2022 | CVPR | Give me your attention: Dot-product attention considered harmful for adversarial patch robustness | - |

| 2021 | CVPR | The Translucent Patch: A Physical and Universal Attack on Object Detectors | Code |

| 2021 | AAAI | Fooling Thermal Infrared Pedestrian Detectors in Real World Using Small Bulbs | - |

| 2021 | Usenix | SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations | Code |

| 2021 | IEEE S&P | Poltergeist: Acoustic Adversarial Machine Learning against Cameras and Computer Vision | Code |

| 2023 | Usenix | TPatch: A Triggered Physical Adversarial Patch | Code |

| 2022 | NDSS | Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems | Project Page |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink | Code |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P43] | [Code][C43] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P44] | [Code][C44] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P45] | [Code][C45] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P46] | [Code][C46] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P47] | [Code][C47] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P48] | [Code][C48] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P49] | [Code][C49] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P50] | [Code][C50] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P51] | [Code][C51] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P52] | [Code][C52] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P53] | [Code][C53] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P54] | [Code][C54] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P55] | [Code][C55] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P56] | [Code][C56] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P57] | [Code][C57] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P58] | [Code][C58] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P59] | [Code][C59] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P60] | [Code][C60] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P61] | [Code][C61] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P62] | [Code][C62] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P63] | [Code][C63] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P64] | [Code][C64] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P65] | [Code][C65] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P66] | [Code][C66] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P67] | [Code][C67] |

| 2021 | CVPR | [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink][P68] | [Code][C68] |

| 2024 | arXiv | MergeOcc: Bridge the Domain Gap between Different LiDARs for Robust Occupancy Prediction | – | | 2023 | T-IV | Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders | Code |

LiDAR-Centric Occupancy Perception

Year	Venue	Paper Title	Link
2017	CVPR		–