中文
相关论文

相关论文: Motivating the Rules of the Game for Adversarial E…

200 篇论文

Machine learning models are increasingly being adopted across various fields, such as medicine, business, autonomous vehicles, and cybersecurity, to analyze vast amounts of data, detect patterns, and make predictions or recommendations. In…

密码学与安全 · 计算机科学 2024-04-16 Dipkamal Bhusal , Nidhi Rastogi

We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to…

The streams of research on adversarial examples and counterfactual explanations have largely been growing independently. This has led to several recent works trying to elucidate their similarities and differences. Most prominently, it has…

机器学习 · 计算机科学 2024-03-18 Tobias Leemann , Martin Pawelczyk , Bardh Prenkaj , Gjergji Kasneci

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at…

机器学习 · 计算机科学 2020-10-26 Florian Tramer , Nicholas Carlini , Wieland Brendel , Aleksander Madry

Tree ensembles are powerful models that are widely used. However, they are susceptible to adversarial examples, which are examples that purposely constructed to elicit a misprediction from the model. This can degrade performance and erode a…

机器学习 · 计算机科学 2022-06-28 Laurens Devos , Wannes Meert , Jesse Davis

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

音频与语音处理 · 电气工程与系统科学 2019-06-10 Yao Qin , Nicholas Carlini , Ian Goodfellow , Garrison Cottrell , Colin Raffel

Deep Neural Networks (DNNs) have shown remarkable performance in a diverse range of machine learning applications. However, it is widely known that DNNs are vulnerable to simple adversarial perturbations, which causes the model to…

机器学习 · 计算机科学 2021-07-23 Gihyuk Ko , Gyumin Lim

Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs),…

机器学习 · 计算机科学 2019-09-24 Jiliang Zhang , Chen Li

Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In…

机器学习 · 计算机科学 2025-11-18 Lucas Fenaux , Christopher Srinivasa , Florian Kerschbaum

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against…

机器学习 · 计算机科学 2019-12-02 Chang Xiao , Changxi Zheng

Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging.…

机器学习 · 计算机科学 2023-09-15 Xinglong Chang , Katharina Dost , Kaiqi Zhao , Ambra Demontis , Fabio Roli , Gill Dobbie , Jörg Wicker

The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these results can be too general to be applicable to natural data…

机器学习 · 计算机科学 2024-05-28 Ambar Pal , Jeremias Sulam , René Vidal

Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet…

机器学习 · 计算机科学 2019-03-26 Jörn-Henrik Jacobsen , Jens Behrmannn , Nicholas Carlini , Florian Tramèr , Nicolas Papernot

This paper considers attacks against machine learning algorithms used in remote sensing applications, a domain that presents a suite of challenges that are not fully addressed by current research focused on natural image data such as…

计算机视觉与模式识别 · 计算机科学 2018-05-29 Wojciech Czaja , Neil Fendley , Michael Pekala , Christopher Ratto , I-Jeng Wang

Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused…

机器学习 · 统计学 2019-09-25 Roi Naveiro , Alberto Redondo , David Ríos Insua , Fabrizio Ruggeri

This paper presents a succinct review of attempts in the literature to use game theory to model decision making scenarios relevant to defence applications. Game theory has been proven as a very effective tool in modelling decision making…

计算机科学与博弈论 · 计算机科学 2021-11-04 Edwin Ho , Arvind Rajagopalan , Alex Skvortsov , Sanjeev Arulampalam , Mahendra Piraveenan

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…

密码学与安全 · 计算机科学 2020-04-01 Mingyi Zhou , Jing Wu , Yipeng Liu , Xiaolin Huang , Shuaicheng Liu , Xiang Zhang , Ce Zhu

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

机器学习 · 计算机科学 2018-01-16 Bo Luo , Yannan Liu , Lingxiao Wei , Qiang Xu

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

人工智能 · 计算机科学 2024-07-09 Lukas Struppek , Minh Hieu Le , Dominik Hintersdorf , Kristian Kersting