mlsanityData to 14 Oct 2026

TkML-AP: Adversarial Attacks to Top-k Multi-Label Learning

arXiv 2108.00146 ↗First posted 31 Jul 2021cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Top-k multi-label learning, which returns the top-k predicted labels from an input, has many practical applications such as image annotation, document analysis, and web search engine. However, the vulnerabilities of such algorithms with regards to dedicated adversarial perturbation attacks have not been extensively studied previously. In this work, we develop methods to create adversarial perturbations that can be used to attack top-k multi-label learning-based image annotation systems (TkML-AP). Our methods explicitly consider the top-k ranking relation and are based on novel loss functions. Experimental evaluations on large-scale benchmark datasets including PASCAL VOC and MS COCO demonstrate the effectiveness of our methods in reducing the performance of state-of-the-art top-k multi-label learning methods, under both untargeted and targeted attacks.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 22 of its 27 references that are in the map. First posted on arXiv 31 Jul 2021.

Builds on

22 of 27 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2021Convex optimizationcited by 2,515
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2016Adversarial Machine Learning at Scalecited by 936
  12. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
10 more
  1. 2016Universal adversarial perturbationscited by 784
  2. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  3. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  4. 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
  5. 2017Learning with Average Top-k Losscited by 52
  6. 2015Top-k Multiclass SVMcited by 28
  7. 2020Learning by Minimizing the Sum of Ranked Rangecited by 27
  8. 2019Multi-Label Adversarial Perturbationscited by 18
  9. 2018A Univariate Bound of Area Under ROCcited by 7
  10. 2020Geometry-Inspired Top-k Adversarial Perturbationscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 10; 2023: 6; 2024: 7; 2025: 2.

26 papers.

Sort:

By area:

  1. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  2. 2021Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Facescited by 48
  3. 2023Improving Fairness in Deepfake Detectioncited by 40
  4. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  5. 2022Rank-based Decomposable Losses in Machine Learning: A Surveycited by 26
  6. 2024Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Imagescited by 20
  7. 2024Robust Light-Weight Facial Affective Behavior Recognition with CLIPcited by 16
  8. 2022Distributionally Robust Survival Analysis: A Novel Fairness Loss Without Demographicscited by 15
  9. 2024Fairness in Survival Analysis with Distributionally Robust Optimizationcited by 14
  10. 2022GAMA: Generative Adversarial Multi-Object Scene Attackscited by 13
  11. 2024Robust COVID-19 Detection in CT Images with CLIPcited by 12
  12. 2022Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Facescited by 11
14 more
  1. 2024Robustly Optimized Deep Feature Decoupling Network for Fatty Liver Diseases Detectioncited by 11
  2. 2023Outlier Robust Adversarial Trainingcited by 10
  3. 2022MultiGuard: Provably Robust Multi-label Classification against Adversarial Examplescited by 9
  4. 2023Data Optimization in Deep Learning: A Surveycited by 6
  5. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  6. 2022Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attackscited by 5
  7. 2025Robust AI-Generated Face Detection with Imbalanced Datacited by 5
  8. 2023Attacking Important Pixels for Anchor-free Detectorscited by 3
  9. 2022Superclass Adversarial Attackcited by 1
  10. 2022Detection of Real-time DeepFakes in Video Conferencing with Active Probing and Corneal Reflectioncited by 1
  11. 2022Synergistic Network Learning and Label Correction for Noise-robust Image Classificationcited by 0
  12. 2023When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-k Multi-Label Learningcited by 0
  13. 2024Showing Many Labels in Multi-label Classification Models: An Empirical Study of Adversarial Examplescited by 0
  14. 2025Semantically Guided Adversarial Testing of Vision Models Using Language Modelscited by 0