# SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications

arXiv: https://arxiv.org/abs/1812.02132 · HTML: https://mlsanity.com/paper/1812.02132/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2018.

## Built on by (most cited first, 12 of 12)

- [Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving](https://mlsanity.com/paper/2101.06784/) (2021)
- [Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation](https://mlsanity.com/paper/2302.07865/) (2023)
- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [SoK: On the Semantic AI Security in Autonomous Driving](https://mlsanity.com/paper/2203.05314/) (2022)
- [DeformRS: Certifying Input Deformations with Randomized Smoothing](https://mlsanity.com/paper/2107.00996/) (2021)
- [Adv3D: Generating 3D Adversarial Examples for 3D Object Detection in Driving Scenarios with NeRF](https://mlsanity.com/paper/2309.01351/) (2023)
- [MVTN: Learning Multi-View Transformations for 3D Understanding](https://mlsanity.com/paper/2212.13462/) (2022)
- [Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning](https://mlsanity.com/paper/2403.05770/) (2024)
- [Conquering Ghosts: Relation Learning for Information Reliability Representation and End-to-End Robust Navigation](https://mlsanity.com/paper/2203.09952/) (2022)
- [A Survey of Neural Network Robustness Assessment in Image Recognition](https://mlsanity.com/paper/2404.08285/) (2024)
- [Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process](https://mlsanity.com/paper/2403.13502/) (2024)
- [Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle](https://mlsanity.com/paper/2309.06313/) (2023)

## Abstract (arXiv)

One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks for DNNs, which mostly focus on pixel-level perturbations void of semantic meaning. In contrast, we present a general framework for adversarial attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks. To do this, we re-frame the adversarial attack problem as learning a distribution of parameters that always fools the agent. In the semantic case, our proposed adversary (denoted as BBGAN) is trained to sample parameters that describe the environment with which the black-box agent interacts, such that the agent performs its dedicated task poorly in this environment. We apply BBGAN on three different tasks, primarily targeting aspects of autonomous navigation: object detection, self-driving, and autonomous UAV racing. On these tasks, BBGAN can generate failure cases that consistently fool a trained agent.