mlsanityData to 7 Oct 2026

Adversarial Diversity and Hard Positive Generation

arXiv 1605.01775 ↗First posted 5 May 2016cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

State-of-the-art deep neural networks suffer from a fundamental problem - they misclassify adversarial examples formed by applying small perturbations to inputs. In this paper, we present a new psychometric perceptual adversarial similarity score (PASS) measure for quantifying adversarial images, introduce the notion of hard positive generation, and use a diverse set of adversarial perturbations - not just the closest ones - for data augmentation. We introduce a novel hot/cold approach for adversarial example generation, which provides multiple possible adversarial perturbations for every single image. The perturbations generated by our novel approach often correspond to semantically meaningful image structures, and allow greater flexibility to scale perturbation-amplitudes, which yields an increased diversity of adversarial images. We present adversarial images on several network topologies and datasets, including LeNet on the MNIST dataset, and GoogLeNet and ResidualNet on the ImageNet dataset. Finally, we demonstrate on LeNet and GoogLeNet that fine-tuning with a diverse set of hard positives improves the robustness of these networks compared to training with prior methods of generating adversarial images.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 7; 2023: 7; 2024: 2; 2025: 2; 2026: 2.

35 papers.

Sort:

  1. 2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  4. 2022Zero-Shot Rumor Detection with Propagation Structure via Prompt Learningcited by 32
  5. 2021Adaptive Image Transformations for Transfer-based Adversarial Attackcited by 22
  6. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
  7. 2023Targeted Adversarial Attacks on Generalizable Neural Radiance Fieldscited by 10
  8. 2022PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Fillingcited by 9
  9. 2021Performance Evaluation of Adversarial Attacks: Discrepancies and Solutionscited by 7
  10. 2021Imperceptible Adversarial Examples by Spatial Chroma-Shiftcited by 7
  11. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  12. 2022Text Transformations in Contrastive Self-Supervised Learning: A Reviewcited by 5
23 more
  1. 2023Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbationscited by 5
  2. 2021Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptionscited by 4
  3. 2022Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundariescited by 4
  4. 2021Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimizationcited by 3
  5. 2021Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbationcited by 3
  6. 2021Frequency Centric Defense Mechanisms against Adversarial Examplescited by 3
  7. 2021Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Gridscited by 2
  8. 2021Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Featurescited by 2
  9. 2023Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Spacecited by 2
  10. 2021PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attackcited by 1
  11. 2022On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problemscited by 1
  12. 2022An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Modelscited by 1
  13. 2023Do we need entire training data for adversarial training?cited by 1
  14. 2023A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detectioncited by 1
  15. 2024COOL: Comprehensive Knowledge Enhanced Prompt Learning for Domain Adaptive Few-shot Fake News Detectioncited by 1
  16. 2021Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challengescited by 0
  17. 2023Contextual Reasoning for Scene Generation (Technical Report)cited by 0
  18. 2023RetouchUAA: Unconstrained Adversarial Attack via Image Retouchingcited by 0
  19. 2024A Survey of Trojan Attacks and Defenses to Deep Neural Networkscited by 0
  20. 2025ANCHOR: Integrating Adversarial Training with Hard-mined Supervised Contrastive Learning for Robust Representation Learningcited by 0
  21. 2025A Generative Adversarial Approach to Adversarial Attacks Guided by Contrastive Language-Image Pre-trained Modelcited by 0
  22. 2026Latent Transfer Attack: Adversarial Examples via Generative Latent Spacescited by 0
  23. 2026Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Gridscited by 0