Selecting Models based on the Risk of Damage Caused by Adversarial Attacks
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.
Code (1)
Similar Papers 제목 키워드 기반
Risk Assessment for Machine Learning Models
In this paper we propose a framework for assessing the risk associated with deploying a machine learning model in a specified environment. For that we carry over the risk definition from decision theory to machine learni…
BIG-bench Machine LearningAttack Tree Analysis for Adversarial Evasion Attacks
Recently, the evolution of deep learning has promoted the application of machine learning (ML) to various systems. However, there are ML systems, such as autonomous vehicles, that cause critical damage when they misclass…
Adversarial AttackAutonomous VehiclesUniversal Adversarial Attack on Attention and the Resulting Dataset DAmageNet
Adversarial attacks on deep neural networks (DNNs) have been found for several years. However, the existing adversarial attacks have high success rates only when the information of the victim DNN is well-known or could b…
Adversarial AttackPrivacy Re-identification Attacks on Tabular GANs
Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generativ…
Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks
Many recent developments in facial landmark detection have been driven by stacking model parameters or augmenting annotations. However, three subsequent challenges remain, including 1) an increase in computational ov…
Face AlignmentFacial Landmark Detection