paper-with-me

홈 › Papers

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

2023-01-28 · Jona Klemenc, Holger Trittenbach

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.

📄 PDF Abstract BibTeX arXiv:2301.12151

Code (1)

duesenfranz/risk_scores_paper_code 공식 구현

Similar Papers 제목 키워드 기반

Risk Assessment for Machine Learning Models

2020-11-09 · Paul Schwerdtner, Florens Greßner, Nikhil Kapoor, Felix Assion 외

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 Learning

Attack Tree Analysis for Adversarial Evasion Attacks

2023-12-28 · Yuki Yamaguchi, Toshiaki Aoki

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 Vehicles

Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet

2020-01-16 · Sizhe Chen, Zhengbao He, Chengjin Sun, Jie Yang 외

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 Attack

Privacy Re-identification Attacks on Tabular GANs

2024-03-31 · Abdallah Alshantti, Adil Rasheed, Frank Westad

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

2021-01-01 · ICCV 2021 10 · Congcong Zhu, Xiaoqiang Li, Jide Li, Songmin Dai

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