paper-with-me

Papers

Robust Testing and Estimation under Manipulation Attacks

2021-04-21 · Jayadev Acharya, Ziteng Sun, Huanyu Zhang

We study robust testing and estimation of discrete distributions in the strong contamination model. We consider both the "centralized setting" and the "distributed setting with information constraints" including communication and local privacy (LDP) constraints. Our technique relates the strength of manipulation attacks to the earth-mover distance using Hamming distance as the metric between messages(samples) from the users. In the centralized setting, we provide optimal error bounds for both learning and testing. Our lower bounds under local information constraints build on the recent lower bound methods in distributed inference. In the communication constrained setting, we develop novel algorithms based on random hashing and an $\ell_1/\ell_1$ isometry.

📄 PDF Abstract BibTeX arXiv:2104.10740

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Invisible Manipulation Deep Reinforcement Learning Enhanced Stealthy Attacks on Battery Energy Management Systems

2024-10-22 · Qi Xiao, Lidong Song, Jongha Woo, Rongxing Hu 외

This paper introduces "invisible manipulation," an innovative cyber-attack mechanism achieved through strategically timed stealthy false data injection attacks (SFDIAs). By stealthily manipulating measurements of a criti…

Deep Reinforcement Learningenergy managementManagementState Estimation+1

Robust Power System State Estimation using Physics-Informed Neural Networks

2025-07-08 · Solon Falas, Markos Asprou, Charalambos Konstantinou, Maria K. Michael arxiv

Modern power systems face significant challenges in state estimation and real-time monitoring, particularly regarding response speed and accuracy under faulty conditions or cyber-attacks. This paper proposes a hybrid app…

Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification

2017-09-17 · Xiaoyu Cao, Neil Zhenqiang Gong

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs a…

ClassificationGeneral ClassificationSelf-Driving Carsspeech-recognition+1

Secure Filtering against Spatio-Temporal False Data Attacks under Asynchronous Sampling

2024-11-29 · Zishuo Li, Anh Tung Nguyen, André M. H. Teixeira, Yilin Mo 외

This paper addresses the secure state estimation problem for continuous linear time-invariant systems with non-periodic and asynchronous sampled measurements, where the sensors need to transmit not only measurements but …

State Estimation

Mate! Are You Really Aware? An Explainability-Guided Testing Framework for Robustness of Malware Detectors

2021-11-19 · Ruoxi Sun, Minhui Xue, Gareth Tyson, Tian Dong 외

Numerous open-source and commercial malware detectors are available. However, their efficacy is threatened by new adversarial attacks, whereby malware attempts to evade detection, e.g., by performing feature-space manipu…