# Overcoming Adversarial Attacks for Human-in-the-Loop Applications

arXiv: https://arxiv.org/abs/2306.05952 · HTML: https://mlsanity.com/paper/2306.05952/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 9 Jun 2023.

## Builds on (most cited first, 8 of 8)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Explanations can be manipulated and geometry is to blame](https://mlsanity.com/paper/1906.07983/) (2019)
- [Towards Robust Explanations for Deep Neural Networks](https://mlsanity.com/paper/2012.10425/) (2020)
- [Detection Defense Against Adversarial Attacks with Saliency Map](https://mlsanity.com/paper/2009.02738/) (2020)
- [A New Ensemble Adversarial Attack Powered by Long-term Gradient Memories](https://mlsanity.com/paper/1911.07682/) (2019)
- [Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective](https://mlsanity.com/paper/2101.03042/) (2021)
- [Adversarial Learning: A Critical Review and Active Learning Study](https://mlsanity.com/paper/1705.09823/) (2017)

## Built on by (most cited first, 1 of 1)

- [Evaluating Adversarial Robustness with Expected Viable Performance](https://mlsanity.com/paper/2309.09928/) (2023)

## Abstract (arXiv)

Including human analysis has the potential to positively affect the robustness of Deep Neural Networks and is relatively unexplored in the Adversarial Machine Learning literature. Neural network visual explanation maps have been shown to be prone to adversarial attacks. Further research is needed in order to select robust visualizations of explanations for the image analyst to evaluate a given model. These factors greatly impact Human-In-The-Loop (HITL) evaluation tools due to their reliance on adversarial images, including explanation maps and measurements of robustness. We believe models of human visual attention may improve interpretability and robustness of human-machine imagery analysis systems. Our challenge remains, how can HITL evaluation be robust in this adversarial landscape?