# Adversarial Diversity and Hard Positive Generation

arXiv: https://arxiv.org/abs/1605.01775 · HTML: https://mlsanity.com/paper/1605.01775/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2016.

## Built on by (most cited first, 30 of 35)

- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2105.14289/) (2021)
- [Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning](https://mlsanity.com/paper/2212.01117/) (2022)
- [Adaptive Image Transformations for Transfer-based Adversarial Attack](https://mlsanity.com/paper/2111.13844/) (2021)
- [Towards Good Practices in Evaluating Transfer Adversarial Attacks](https://mlsanity.com/paper/2211.09565/) (2022)
- [Targeted Adversarial Attacks on Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2310.03578/) (2023)
- [PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling](https://mlsanity.com/paper/2208.11508/) (2022)
- [Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions](https://mlsanity.com/paper/2104.11103/) (2021)
- [Imperceptible Adversarial Examples by Spatial Chroma-Shift](https://mlsanity.com/paper/2108.02502/) (2021)
- [Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks](https://mlsanity.com/paper/2106.07141/) (2021)
- [Text Transformations in Contrastive Self-Supervised Learning: A Review](https://mlsanity.com/paper/2203.12000/) (2022)
- [Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations](https://mlsanity.com/paper/2310.03518/) (2023)
- [Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions](https://mlsanity.com/paper/2103.11002/) (2021)
- [Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundaries](https://mlsanity.com/paper/2208.08697/) (2022)
- [Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization](https://mlsanity.com/paper/2101.07512/) (2021)
- [Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation](https://mlsanity.com/paper/2102.08079/) (2021)
- [Frequency Centric Defense Mechanisms against Adversarial Examples](https://mlsanity.com/paper/2110.13935/) (2021)
- [Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids](https://mlsanity.com/paper/2102.09057/) (2021)
- [Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features](https://mlsanity.com/paper/2107.09502/) (2021)
- [Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space](https://mlsanity.com/paper/2302.09484/) (2023)
- [PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack](https://mlsanity.com/paper/2101.07538/) (2021)
- [On the Feasibility and Generality of Patch-based Adversarial Attacks on Semantic Segmentation Problems](https://mlsanity.com/paper/2205.10539/) (2022)
- [An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models](https://mlsanity.com/paper/2208.07464/) (2022)
- [Do we need entire training data for adversarial training?](https://mlsanity.com/paper/2303.06241/) (2023)
- [A Unified Contrastive Transfer Framework with Propagation Structure for Boosting Low-Resource Rumor Detection](https://mlsanity.com/paper/2304.01492/) (2023)
- [COOL: Comprehensive Knowledge Enhanced Prompt Learning for Domain Adaptive Few-shot Fake News Detection](https://mlsanity.com/paper/2406.10870/) (2024)
- [Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges](https://mlsanity.com/paper/2107.02894/) (2021)
- [Contextual Reasoning for Scene Generation (Technical Report)](https://mlsanity.com/paper/2305.02255/) (2023)
- [RetouchUAA: Unconstrained Adversarial Attack via Image Retouching](https://mlsanity.com/paper/2311.16478/) (2023)

## 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.