mlsanityData to 7 Oct 2026

Maximal Jacobian-based Saliency Map Attack

arXiv 1808.07945 ↗First posted 23 Aug 2018cs.LG stat.MLcited by 46

Not on the map. Why?

Abstract (arXiv)

The Jacobian-based Saliency Map Attack is a family of adversarial attack methods for fooling classification models, such as deep neural networks for image classification tasks. By saturating a few pixels in a given image to their maximum or minimum values, JSMA can cause the model to misclassify the resulting adversarial image as a specified erroneous target class. We propose two variants of JSMA, one which removes the requirement to specify a target class, and another that additionally does not need to specify whether to only increase or decrease pixel intensities. Our experiments highlight the competitive speeds and qualities of these variants when applied to datasets of hand-written digits and natural scenes.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 11; 2023: 8; 2024: 9; 2025: 7; 2026: 1.

46 papers.

Sort:

By area:

  1. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 40
  2. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
  3. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  4. 2025A Survey on Efficient Vision-Language Modelscited by 19
  5. 2021Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Votingcited by 16
  6. 2021Adversarial Token Attacks on Vision Transformerscited by 11
  7. 2021Sparse Adversarial Video Attacks with Spatial Transformationscited by 11
  8. 2022Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNscited by 11
  9. 2022Adversarial Color Film: Effective Physical-World Attack to DNNscited by 11
  10. 2021Launching Adversarial Attacks against Network Intrusion Detection Systems for IoTcited by 9
  11. 2022Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT datacited by 7
  12. 2022Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generatorcited by 5
34 more
  1. 2021Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilitiescited by 4
  2. 2022Adversarial Zoom Lens: A Novel Physical-World Attack to DNNscited by 4
  3. 2024Red-Teaming Segment Anything Modelcited by 4
  4. 2025Breach in the Shield: Unveiling the Vulnerabilities of Large Language Modelscited by 4
  5. 2025Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithmcited by 3
  6. 2022A Tutorial on Adversarial Learning Attacks and Countermeasurescited by 2
  7. 2023AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Trainingcited by 2
  8. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  9. 2024JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Examplecited by 2
  10. 2025GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Modelscited by 2
  11. 2021Robustness-via-Synthesis: Robust Training with Generative Adversarial Perturbationscited by 1
  12. 2022Adversarial Color Projection: A Projector-based Physical Attack to DNNscited by 1
  13. 2022Adversarial Catoptric Light: An Effective, Stealthy and Robust Physical-World Attack to DNNscited by 1
  14. 2023Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundarycited by 1
  15. 2025Detecting and Mitigating DDoS Attacks with AI: A Surveycited by 1
  16. 2021Fast Approximate Spectral Normalization for Robust Deep Neural Networkscited by 0
  17. 2021Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognitioncited by 0
  18. 2022Impact of Scaled Image on Robustness of Deep Neural Networkscited by 0
  19. 2022Impact of Colour Variation on Robustness of Deep Neural Networkscited by 0
  20. 2023Impact of Light and Shadow on Robustness of Deep Neural Networkscited by 0
  21. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  22. 2023GMTR: Graph Matching Transformerscited by 0
  23. 2023Universal Adversarial Framework to Improve Adversarial Robustness for Diabetic Retinopathy Detectioncited by 0
  24. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  25. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  26. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  27. 2024NeuralSentinel: Safeguarding Neural Network Reliability and Trustworthinesscited by 0
  28. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  29. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  30. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  31. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  32. 2025Adversarial Attacks in Multimodal Systems: A Practitioner's Surveycited by 0
  33. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  34. 2026Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Modelscited by 0