# Selecting Models based on the Risk of Damage Caused by Adversarial Attacks

arXiv: https://arxiv.org/abs/2301.12151 · HTML: https://mlsanity.com/paper/2301.12151/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 28 Jan 2023.

## Builds on (most cited first, 19 of 19)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Unlabeled Data Improves Adversarial Robustness](https://mlsanity.com/paper/1905.13736/) (2019)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Adversarial Risk and the Dangers of Evaluating Against Weak Attacks](https://mlsanity.com/paper/1802.05666/) (2018)
- [An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models](https://mlsanity.com/paper/2002.02175/) (2020)
- [A Statistical Approach to Assessing Neural Network Robustness](https://mlsanity.com/paper/1811.07209/) (2018)
- [Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution](https://mlsanity.com/paper/1810.12272/) (2018)
- [The Many Faces of Adversarial Risk](https://mlsanity.com/paper/2201.08956/) (2022)
- [RoMA: a Method for Neural Network Robustness Measurement and Assessment](https://mlsanity.com/paper/2110.11088/) (2021)
- [Adversarial Vision Challenge](https://mlsanity.com/paper/1808.01976/) (2018)
- [Quantitative AI Risk Assessments: Opportunities and Challenges](https://mlsanity.com/paper/2209.06317/) (2022)
- [Risk Assessment for Machine Learning Models](https://mlsanity.com/paper/2011.04328/) (2020)
- [RoBIC: A benchmark suite for assessing classifiers robustness](https://mlsanity.com/paper/2102.05368/) (2021)

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

- [A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lighting](https://mlsanity.com/paper/2408.06071/) (2024)

## Abstract (arXiv)

Regulation, legal liabilities, and societal concerns challenge the adoption of AI in safety and security-critical applications. One of the key concerns is that adversaries can cause harm by manipulating model predictions without being detected. Regulation hence demands an assessment of the risk of damage caused by adversaries. Yet, there is no method to translate this high-level demand into actionable metrics that quantify the risk of damage. In this article, we propose a method to model and statistically estimate the probability of damage arising from adversarial attacks. We show that our proposed estimator is statistically consistent and unbiased. In experiments, we demonstrate that the estimation results of our method have a clear and actionable interpretation and outperform conventional metrics. We then show how operators can use the estimation results to reliably select the model with the lowest risk.