In this work, we propose a peer-to-peer (P2P) learning scheme that is secure against malicious servers and robust to malicious clients.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Former Vice President Kamala Harris addresses delegates with the Democratic National Committee at their winter meeting in downtown Los Angeles on Friday. This is read by an automated voice. Please report any issues or inconsistencies here . California's two most prominent Democrats, former Vice President Kamala Harris and Gov. Gavin Newsom, addressed national Democratic leaders in L.A.

Collaborative and distributed learning techniques, such as Federated Learning (FL) and Split Learning (SL), hold significant promise for leveraging sensitive data in privacy-critical domains. However, FL and SL suffer from key limitations -- FL imposes substantial computational demands on clients, while SL leads to prolonged training times. To overcome these challenges, SplitFed Learning (SFL) was introduced as a hybrid approach that combines the strengths of FL and SL. Despite its advantages, SFL inherits scalability, performance, and security issues from SL. In this paper, we propose two novel frameworks: Sharded SplitFed Learning (SSFL) and Blockchain-enabled SplitFed Learning (BSFL). SSFL addresses the scalability and performance constraints of SFL by distributing the workload and communication overhead of the SL server across multiple parallel shards. Building upon SSFL, BSFL replaces the centralized server with a blockchain-based architecture that employs a committee-driven consensus mechanism to enhance fairness and security. BSFL incorporates an evaluation mechanism to exclude poisoned or tampered model updates, thereby mitigating data poisoning and model integrity attacks. Experimental evaluations against baseline SL and SFL approaches show that SSFL improves performance and scalability by 31.2% and 85.2%, respectively. Furthermore, BSFL increases resilience to data poisoning attacks by 62.7% while maintaining superior performance under normal operating conditions. To the best of our knowledge, BSFL is the first blockchain-enabled framework to implement an end-to-end decentralized SplitFed Learning system.

Questions in political interviews and hearings serve strategic purposes beyond information gathering including advancing partisan narratives and shaping public perceptions. However, these strategic aspects remain understudied due to the lack of large-scale datasets for studying such discourse. Congressional hearings provide an especially rich and tractable site for studying political questioning: Interactions are structured by formal rules, witnesses are obliged to respond, and members with different political affiliations are guaranteed opportunities to ask questions, enabling comparisons of behaviors across the political spectrum. We develop a pipeline to extract question-answer pairs from unstructured hearing transcripts and construct a novel dataset of committee hearings from the 108th--117th Congress. Our analysis reveals systematic differences in questioning strategies across parties, by showing the party affiliation of questioners can be predicted from their questions alone. Our dataset and methods not only advance the study of congressional politics, but also provide a general framework for analyzing question-answering across interview-like settings.

This paper is concerned with an observation about adaptive data analysis. It relies on a study that shows that despite statistical lower bounds, common practices of adaptive data analysis do not result in overfitting. The authors show that empirically this is a result of the models used in Kaggle competitions behaving in a similar manner. In addition, the authors give a simple model and analyze the model. The reviewers thought this is an interesting direction and that the results were generally well executed.

Our work aims to minimize interaction in secure computation due to the high cost and challenges associated with communication rounds, particularly in scenarios with many clients. In this work, we revisit the problem of secure aggregation in the single-server setting where a single evaluation server can securely aggregate client-held individual inputs. Our key contribution is the introduction of One-shot Private Aggregation ($\mathsf{OPA}$) where clients speak only once (or even choose not to speak) per aggregation evaluation. Since each client communicates only once per aggregation, this simplifies managing dropouts and dynamic participation, contrasting with multi-round protocols and aligning with plaintext secure aggregation, where clients interact only once. We construct $\mathsf{OPA}$ based on LWR, LWE, class groups, DCR and demonstrate applications to privacy-preserving Federated Learning (FL) where clients \emph{speak once}. This is a sharp departure from prior multi-round FL protocols whose study was initiated by Bonawitz et al. (CCS, 2017). Moreover, unlike the YOSO (You Only Speak Once) model for general secure computation, $\mathsf{OPA}$ eliminates complex committee selection protocols to achieve adaptive security. Beyond asymptotic improvements, $\mathsf{OPA}$ is practical, outperforming state-of-the-art solutions. We benchmark logistic regression classifiers for two datasets, while also building an MLP classifier to train on MNIST, CIFAR-10, and CIFAR-100 datasets. We build two flavors of $\caps$ (1) from (threshold) key homomorphic PRF and (2) from seed homomorphic PRG and secret sharing.

When the Swedish inventor Alfred Nobel wrote his will in 1895, he designated funds to reward those who "have conferred the greatest benefit to humankind." The resulting Nobel Prizes have since been awarded to the discoverers of penicillin, X-rays, and the structure of DNA--and, as of today, to two scientists who, decades ago, laid the foundations for modern artificial intelligence. Today, John Hopfield and Geoffrey Hinton received the Nobel Prize in Physics for groundbreaking statistical methods that have advanced physics, chemistry, biology, and more. In the announcement, Ellen Moons, the chair of the Nobel Committee for Physics and a physicist at Karlstad University, celebrated the two laureates' work, which used "fundamental concepts from statistical physics to design artificial neural networks" that can "find patterns in large data sets." She mentioned applications of their research in astrophysics and medical diagnosis, as well as in daily technologies such as facial recognition and language translation.

Approval-based committee (ABC) voting represents a well-studied multiwinner election setting, where a subset of candidates of a predetermined size, a so-called committee, needs to be chosen based on the approval preferences of a set of voters [23]. Traditionally, ABC voting is studied in the context where we know, for each voter and each candidate, whether the voter approves the candidate or not. In this paper, we investigate the situation where the approval information is incomplete. Specifically, we assume that each voter is associated with a set of approved candidates, a set of disapproved candidates, and a set of candidates where the voter's stand is unknown, hereafter referred to as the unknown candidates. Moreover, we may have (partial) ordinal information on voters' preferences among the unknown candidates, restricting the "valid" completions of voters' approval sets. When the number of candidates is large, unknown candidates are likely to exist because voters are not aware of or not familiar with, and therefore cannot evaluate, all candidates. In particular, this holds in scenarios where candidates join the election over time, and voter preferences over new candidates have not been elicited [16].

Work was done while Ge-Peng Ji was a research intern at Alibaba Group. The authors declared that they have no conflicts of interest in this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted. Ge-Peng Ji received the M. Sc. degree in communication and information systems from Wuhan University, China in 2021. He is currently a Ph.D. degree candidate at Australian National University, supervised by Professor Nick Barnes, majoring in engineering and computer science.