mlsanityData to 7 Oct 2026

UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems

arXiv 2604.23362 ↗First posted 25 Apr 2026cs.SE cs.LGcited by 0

On the map: End-to-end autonomous driving → Adversarial scenarios and safety testing

Abstract (arXiv)

Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to the input can elicit erroneous outcomes, thereby substantially compromising the security of DL systems. This has emerged as a critical concern in the development of DL-based safety-critical systems like Autonomous Driving Systems (ADSs). The focus of existing adversarial attack methods on End-to-End (E2E) ADSs has predominantly centered on misbehaviors of steering angle, which overlooks speed-related controls or imperceptible perturbations. To address these challenges, we introduce UniAda, a multi-objective white-box attack technique with a core function that revolves around crafting an image-agnostic adversarial perturbation capable of simultaneously influencing both steering and speed controls. UniAda capitalizes on an intricately designed multi-objective optimization function with the Adaptive Weighting Scheme (AWS), enabling the concurrent optimization of diverse objectives. Validated with both simulated and real-world driving data, UniAda outperforms five benchmarks across two metrics, inducing steering and speed deviations from 3.54 degrees to 29 degrees and 11 km per hour to 22 km per hour on average. This systematic approach establishes UniAda as a proven technique for adversarial attacks on modern DL-based E2E ADSs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving. Builds on 31 of its 53 references that are in the map. First posted on arXiv 25 Apr 2026.

Builds on

31 of 53 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles6 Aug
  2. 2021Adversarial Driving: Attacking End-to-End Autonomous Driving16 Mar

Other references · 29

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Adversarial examples in the physical worldcited by 1,762
  4. 2016End to End Learning for Self-Driving Carscited by 1,000
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  8. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  9. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  10. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  11. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  12. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
17 more
  1. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  2. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  3. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  4. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  5. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 211
  6. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 123
  7. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  8. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 101
  9. 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
  10. 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 67
  11. 2018On Offline Evaluation of Vision-based Driving Modelscited by 62
  12. 2021A Survey On Universal Adversarial Attackcited by 59
  13. 2019Misbehaviour Prediction for Autonomous Driving Systemscited by 55
  14. 2018DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systemscited by 50
  15. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 29
  16. 2019Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Studycited by 27
  17. 2022Self-Driving Car Steering Angle Prediction: Let Transformer Be a Car Againcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
  2. 2024Attack End-to-End Autonomous Driving through Module-Wise Noise
  3. 2026Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures
  4. 2026AD2: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems
  5. 2026Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis
  6. 2025Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems
  7. 2024Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
  8. 2025Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving