mlsanityData to 14 Oct 2026

ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments

arXiv 2607.17077 ↗First posted 19 Jul 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and differentiable rendering enables more robust, end-to-end evaluation of these adversarial attacks, yet there is no easy-to-use, unified system that offers a rich set of customizable configurations for adversarial attacks across multiple scenes, objects, environmental and lighting conditions, and camera trajectories. We present ALLUDE, which addresses these gaps, offering first-of-its-kind evaluation capabilities across Linux and Windows. We comprehensively demonstrate ALLUDE's evaluation breadth through a two-pronged strategy: (1) using Latin Hypercube Sampling, we draw a representative subset from 5,400 configurations spanning 10 scene-object pairs, 9 weather conditions, 4 optimizers, 5 camera trajectories, and 3 detection models; (2) we stress-test existing attacks (CAMOU, RAUCA, FCA) under diverse weather conditions and continuous camera trajectories, revealing degradation of attack success across every attack, exposing evaluation gaps in prior work. Through ALLUDE's end-to-end differentiable rendering, adversarial attacks can be optimized against shifting real-world deployment conditions. Our cross-platform code is open source.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 19 Jul 2026.

Builds on

19 of 30 references.

References · 19

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  3. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  4. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  5. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  6. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  7. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  8. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  9. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  10. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  11. 2020Physical Adversarial Attack on Vehicle Detector in the Carla Simulatorcited by 38
  12. 2024Visual Adversarial Attack on Vision-Language Models for Autonomous Drivingcited by 36
7 more
  1. 2023ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasioncited by 31
  2. 2023SynDrone -- Multi-modal UAV Dataset for Urban Scenarioscited by 28
  3. 2024RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generationcited by 18
  4. 2023SkyScenes: A Synthetic Dataset for Aerial Scene Understandingcited by 13
  5. 2024Flexible Physical Camouflage Generation Based on a Differential Approachcited by 7
  6. 2024Imperceptible Adversarial Examples in the Physical Worldcited by 2
  7. 2025UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attackscited by 1

Built on by

Not cited yet.