检索结果-内蒙古大学图书馆

5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022

作者： Struppek, Lukas Hintersdorf, Dominik Neider, Daniel Kersting, Kristian Department of Computer Science Technical University of Darmstadt Darmstadt Germany Max Planck Institute for Software Systems Kaiserslautern Germany Safety and Explainability of Learning Systems Carl von Ossietzky University of Oldenburg Kaiserslautern Germany Department of Computer Science and Centre for Cognitive Science Technical University of Darmstadt Darmstadt Germany Hessian Center for Artificial Intelligence Darmstadt Germany

ISBN: (纸本)9781450393522

Apple recently revealed its deep perceptual hashing system NeuralHash to detect child sexual abuse material (CSAM) on user devices before files are uploaded to its iCloud service. Public criticism quickly arose regarding the protection of user privacy and the system's reliability. In this paper, we present the first comprehensive empirical analysis of deep perceptual hashing based on NeuralHash. Specifically, we show that current deep perceptual hashing may not be robust. An adversary can manipulate the hash values by applying slight changes in images, either induced by gradient-based approaches or simply by performing standard image transformations, forcing or preventing hash collisions. Such attacks permit malicious actors easily to exploit the detection system: from hiding abusive material to framing innocent users, everything is possible. Moreover, using the hash values, inferences can still be made about the data stored on user devices. In our view, based on our results, deep perceptual hashing in its current form is generally not ready for robust client-side scanning and should not be used from a privacy perspective.1 © 2022 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robustness-by-Construction Synthesis: Adapting to the Environment at Runtime

arXiv

引用

arXiv 2022年

作者： Nayak, Satya Prakash Neider, Daniel Zimmermann, Martin Max Planck Institute for Software Systems Kaiserslautern Germany Safety and Explainability of Learning Systems Group Carl von Ossietzky Universität Oldenburg Oldenburg Germany Aalborg University Aalborg Denmark

While most of the current synthesis algorithms only focus on correctness-by-construction, ensuring robustness has remained a challenge. Hence, in this paper, we address the robust-by-construction synthesis problem by considering the specifications to be expressed by a robust version of Linear Temporal Logic (LTL), called robust LTL (rLTL). rLTL has a many-valued semantics to capture different degrees of satisfaction of a specification, i.e., satisfaction is a quantitative notion. We argue that the current algorithms for rLTL synthesis do not compute optimal strategies in a non-antagonistic setting. So, a natural question is whether there is a way of satisfying the specification "better" if the environment is indeed not antagonistic. We address this question by developing two new notions of strategies. The first notion is that of adaptive strategies, which, in response to the opponent's non-antagonistic moves, maximize the degree of satisfaction. The idea is to monitor non-optimal moves of the opponent at runtime using multiple parity automata and adaptively change the system strategy to ensure optimality. The second notion is that of strongly adaptive strategies, which is a further refinement of the first notion. These strategies also maximize the opportunities for the opponent to make non-optimal moves. We show that computing such strategies for rLTL specifications is not harder than the standard synthesis problem, e.g., computing strategies with LTL specifications, and takes doubly-exponential time. Copyright © 2022, The Authors. All rights reserved.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

From LTL to rLTL Monitoring: Improved Monitorability through Robust Semantics

arXiv

引用

arXiv 2018年

作者： Mascle, Corto Neider, Daniel Schwenger, Maximilian Tabuada, Paulo Weinert, Alexander Zimmermann, Martin ENS Paris-Saclay Cachan France Safety and Explainability of Learning Systems Group Carl von Ossietzky University of Oldenburg Germany The Max Planck Institute for Software Systems Kaiserslautern Germany Reactive Systems Group Saarland University Saarbrücken Germany Department of Electrical and Computer Engineering UCLA Los Angeles United States Cologne Germany University of Liverpool Liverpool United Kingdom

Runtime monitoring is commonly used to detect the violation of desired properties in safety critical cyber-physical systems by observing its executions. Bauer et al. introduced an influential framework for monitoring Linear Temporal Logic (LTL) properties based on a three-valued semantics for a finite execution: the formula is already satisfied by the given execution, it is already violated, or it is still undetermined, i.e., it can still be satisfied and violated by appropriate extensions of the given execution. However, a wide range of formulas are not monitorable under this approach, meaning that there are executions for which satisfaction and violation will always remain undetermined no matter how it is extended. In particular, Bauer et al. report that 44% of the formulas they consider in their experiments fall into this category. Recently, a robust semantics for LTL was introduced to capture different degrees by which a property can be violated. In this paper we introduce a robust semantics for finite strings and show its potential in monitoring: every formula considered by Bauer et al. is monitorable under our approach. Furthermore, we discuss which properties that come naturally in LTL monitoring - such as the realizability of all truth values - can be transferred to the robust setting. We show that LTL formulas with robust semantics can be monitored by deterministic automata, and provide tight bounds on the size of the constructed automaton. Lastly, we report on a prototype implementation and compare it to the LTL monitor of Bauer et al. on a sample of examples. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：