mlsanityData to 7 Oct 2026

Houdini: Fooling Deep Structured Prediction Models

arXiv 1707.05373 ↗First posted 17 Jul 2017stat.ML cs.AI cs.CRcited by 50

Not on the map. Why?

Abstract (arXiv)

Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable. We successfully apply Houdini to a range of applications such as speech recognition, pose estimation and semantic segmentation. In all cases, the attacks based on Houdini achieve higher success rate than those based on the traditional surrogates used to train the models while using a less perceptible adversarial perturbation.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 11; 2023: 7; 2024: 12; 2025: 2; 2026: 1.

50 papers.

Sort:

By area:

  1. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  2. 2024AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Modelscited by 33
  3. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  4. 2021Parameter identifiability of a deep feedforward ReLU neural networkcited by 24
  5. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  6. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  7. 2024Towards Adversarially Robust Dataset Distillation by Curvature Regularizationcited by 17
  8. 2021Towards Robust General Medical Image Segmentationcited by 14
  9. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  10. 2022Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detectioncited by 13
  11. 2023Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Modelscited by 12
  12. 2024Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Modelscited by 12
38 more
  1. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  2. 2021Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Modelscited by 10
  3. 2021Black-box Adversarial Attacks in Autonomous Vehicle Technologycited by 9
  4. 2021Generalized Real-World Super-Resolution through Adversarial Robustnesscited by 9
  5. 2022Robust Perception through Equivariancecited by 9
  6. 2023Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentationcited by 9
  7. 2021Hybrid Classical-Quantum Deep Learning Models for Autonomous Vehicle Traffic Image Classification Under Adversarial Attackcited by 5
  8. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5
  9. 2023Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentationcited by 5
  10. 2025Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMscited by 5
  11. 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
  12. 2021StyleLess layer: Improving robustness for real-world drivingcited by 4
  13. 2022Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detectioncited by 4
  14. 2022Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Surveycited by 3
  15. 2025Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generationcited by 3
  16. 2022Surround-View Cameras based Holistic Visual Perception for Automated Drivingcited by 2
  17. 2024A Survey of Neural Network Robustness Assessment in Image Recognitioncited by 2
  18. 2024BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimizationcited by 2
  19. 2024Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Modelscited by 2
  20. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  21. 2021Model-Agnostic Defense for Lane Detection against Adversarial Attackcited by 1
  22. 2021Improving Global Adversarial Robustness Generalization With Adversarially Trained GANcited by 1
  23. 2021Localized Uncertainty Attackscited by 1
  24. 2022Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Maskingcited by 1
  25. 2022Trace and Detect Adversarial Attacks on CNNs using Feature Response Mapscited by 1
  26. 2022Leveraging Domain Features for Detecting Adversarial Attacks Against Deep Speech Recognition in Noisecited by 1
  27. 2024Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attackscited by 1
  28. 2024Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysiscited by 1
  29. 2021Context-Aware Image Denoising with Auto-Threshold Canny Edge Detection to Suppress Adversarial Perturbationcited by 0
  30. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 0
  31. 2021Mitigating Gradient-based Adversarial Attacks via Denoising and Compressioncited by 0
  32. 2022Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Trainingcited by 0
  33. 2022Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learningcited by 0
  34. 2022Securing AI-based Healthcare Systems using Blockchain Technology: A State-of-the-Art Systematic Literature Review and Future Research Directionscited by 0
  35. 2023On the Trade-offs between Adversarial Robustness and Actionable Explanationscited by 0
  36. 2023A Survey of Adversarial CAPTCHAs on its History, Classification and Generationcited by 0
  37. 2024Sequencing the Neurome: Towards Scalable Exact Parameter Reconstruction of Black-Box Neural Networkscited by 0
  38. 2026Operational Robustness of LLMs on Code Generationcited by 0