{"title":"Human Feedback Attack on Online RLHF: Attack and Robust Defense","authors":"Chenye Yang, Mo Lyu, Guanlin Liu, Lifeng Lai","doi":"10.1109/tsp.2025.3607114","DOIUrl":"https://doi.org/10.1109/tsp.2025.3607114","url":null,"abstract":"","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"11 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145017533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Malek Khammassi;Virginia Bordignon;Vincenzo Matta;Ali H. Sayed
{"title":"Adaptive Social Learning for Slow Markov Chains","authors":"Malek Khammassi;Virginia Bordignon;Vincenzo Matta;Ali H. Sayed","doi":"10.1109/TSP.2025.3606580","DOIUrl":"10.1109/TSP.2025.3606580","url":null,"abstract":"This paper studies the problem of interconnected agents collaborating to track a dynamic state from partially informative observations, where the state follows a slow finite-state Markov chain. While the centralized version of this problem is well understood, the decentralized setting warrants further exploration. This work aims to demonstrate that a decentralized social learning strategy can achieve the same error probability scaling law in the rare transitions regime as the optimal centralized solution. To study this problem, we focus on adaptive social learning (ASL), a recent strategy developed for non-stationary environments, and analyze its performance when the agents’ observations are governed by a hidden, slow Markov chain. Our study yields two key findings. First, we demonstrate that the ASL adaptation performance is closely linked to the dynamics of the underlying Markov chain, achieving a vanishing steady-state error probability when the average drift time of the Markov chain exceeds the ASL adaptation time. Second, we derive a closed-form upper bound for the ASL steady-state error probability in the rare transition regime, showing that it decays similarly to the optimal centralized solution. Simulations illustrate our theoretical findings and provide a comparative analysis with existing strategies.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"3671-3687"},"PeriodicalIF":5.8,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145017536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A 1.5-bit Quantization Scheme and Its Application to Direction Estimation","authors":"Xicheng Lu, Wei Liu, Akram Alomainy","doi":"10.1109/tsp.2025.3604889","DOIUrl":"https://doi.org/10.1109/tsp.2025.3604889","url":null,"abstract":"","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"24 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145003019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shan Sha;Shenglong Zhou;Lingchen Kong;Geoffrey Ye Li
{"title":"Sparse Decentralized Federated Learning","authors":"Shan Sha;Shenglong Zhou;Lingchen Kong;Geoffrey Ye Li","doi":"10.1109/TSP.2025.3603005","DOIUrl":"10.1109/TSP.2025.3603005","url":null,"abstract":"Decentralized Federated Learning (DFL) enables collaborative model training without a central server but faces challenges in efficiency, stability, and trustworthiness due to communication and computational limitations among distributed nodes. To address these critical issues, we introduce a sparsity constraint on the shared model, leading to Sparse DFL (SDFL), and propose a novel algorithm, CEPS. The sparsity constraint facilitates the use of one-bit compressive sensing to transmit one-bit information between partially selected neighbour nodes at specific steps, thereby significantly improving communication efficiency. Moreover, we integrate differential privacy into the algorithm to ensure privacy preservation and bolster the trustworthiness of the learning process. Furthermore, CEPS is underpinned by theoretical guarantees regarding both convergence and privacy. Numerical experiments validate the effectiveness of the proposed algorithm in improving communication and computation efficiency while maintaining a high level of trustworthiness.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"3406-3420"},"PeriodicalIF":5.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144927950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Orthogonal Fourier Analysis on Directed Acyclic Graphs via Möbius Total Variation","authors":"Vedran Mihal, Markus Püschel","doi":"10.1109/tsp.2025.3603696","DOIUrl":"https://doi.org/10.1109/tsp.2025.3603696","url":null,"abstract":"","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"92 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144927947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Unified Penalty Method for Maximum Likelihood Estimation of Gaussian and Student’s t GARCH","authors":"Chenyu Gao, Ziping Zhao, Daniel P. Palomar","doi":"10.1109/tsp.2025.3604632","DOIUrl":"https://doi.org/10.1109/tsp.2025.3604632","url":null,"abstract":"","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"14 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144927946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Siyuan Jiang;Shuai Liu;Feng-Gang Yan;Fulvio Gini;Maria Sabrina Greco;Ming Jin
{"title":"Over-Relaxed ADMM-Based Unitary Adaptive Beamforming Scheme With Lobe-Level Constraints","authors":"Siyuan Jiang;Shuai Liu;Feng-Gang Yan;Fulvio Gini;Maria Sabrina Greco;Ming Jin","doi":"10.1109/TSP.2025.3603307","DOIUrl":"10.1109/TSP.2025.3603307","url":null,"abstract":"The performance of adaptive beamforming may degrade dramatically in a highly dynamic environment, because the directions of arrival (DOAs) of targets and interferences can change rapidly. To address this problem, we propose here to introduce additional mainlobe-level and sidelobe-level constraints in the design problem, with the goal to broaden the mainlobe and the nulls of the beampattern. However, the solution of the resulting optimization problem with non-convex constraints has high computational complexity. To reduce it, we propose to transform the complex-valued non-convex constrained optimization problem into a real-valued convex constrained one by performing a unitary transformation, which is suitable for centro-symmetric arrays (CSA). Then, the problem is decomposed into multiple unconstrained optimization sub-problems that can be solved iteratively using the standard alternating direction method of multipliers (S-ADMM) method. To improve further the convergence speed, we then develop an over-relaxed ADMM (OR-ADMM) by exploiting the principle of relaxation. Numerical simulation demonstrates the robustness and the convergence speed improvements of the proposed OR-ADMM in a highly dynamic environment.","PeriodicalId":13330,"journal":{"name":"IEEE Transactions on Signal Processing","volume":"73 ","pages":"3656-3670"},"PeriodicalIF":5.8,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144919540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}