An AI-powered smart home voice assistant that amiably chats with you, follows your orders with ease, and does your bidding in the background? It's a tantalizing idea that seems so close, yet remains stubbornly far away. The big prediction last year was that a new Apple smart hub powered by an AI-augmented Siri would arrive by spring 2025--right around now--complete with a touchscreen and smart home controls. It was a device that would vault Apple back into the smart home game. And then there was Google, which had begun testing Gemini on its Nest smart speakers late last year, allowing a small subset of its users to chat with the powerful AI model when asking more complex questions.

In this study, we establish a unified framework to deal with the high dimensional matrix completion problem under flexible nonignorable missing mechanisms. Although the matrix completion problem has attracted much attention over the years, there are very sparse works that consider the nonignorable missing mechanism. To address this problem, we derive a row- and column-wise matrix U-statistics type loss function, with the nuclear norm for regularization. A singular value proximal gradient algorithm is developed to solve the proposed optimization problem. We prove the non-asymptotic upper bound of the estimation error's Frobenius norm and show the performance of our method through numerical simulations and real data analysis.

We study how to use naturally available user feedback, such as clicks, to optimize large language model (LLM) pipelines for generating personalized sentences using prompts. Naive approaches, which estimate the policy gradient in the prompt space, suffer either from variance caused by the large action space of prompts or bias caused by inaccurate reward predictions. To circumvent these challenges, we propose a novel kernel-based off-policy gradient method, which estimates the policy gradient by leveraging similarity among generated sentences, substantially reducing variance while suppressing the bias. Empirical results on our newly established suite of benchmarks demonstrate the effectiveness of the proposed approach in generating personalized descriptions for movie recommendations, particularly when the number of candidate prompts is large.

A huge data breach has leaked over 50,000 profiles from the'Gay Daddy' dating app, cybersecurity researchers have discovered. The exposed data contains extremely sensitive information including users' names, ages, location data and HIV status. According to experts from Cybernews, the exposed database also contains over 124,000 private messages and photos – many of which are explicit. While the app markets itself as a'private and anonymous community', researchers say the information could be accessed by anyone with'basic technical knowledge'. Researchers say the app's'devastating' security failure puts its users at serious risk of blackmail, exploitation and even physical harm.

NN, MM YYYY 1 SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Models Jinho Y ang, Graduate Student Member, IEEE, Ji-Hoon Kim, Graduate Student Member, IEEE, Joo-Y oung Kim, Senior Member, IEEE, Abstract --Deep Learning Recommendation Models (DLRMs) play a crucial role in delivering personalized content across web applications such as social networking and video streaming. However, with improvements in performance, the parameter size of DLRMs has grown to terabyte (TB) scales, accompanied by memory bandwidth demands exceeding TB/s levels. Furthermore, the workload intensity within the model varies based on the target mechanism, making it difficult to build an optimized recommendation system. In this paper, we propose SCRec, a scalable computational storage recommendation system that can handle TB-scale industrial DLRMs while guaranteeing high bandwidth requirements. SCRec utilizes a software framework that features a mixed-integer programming (MIP)-based cost model, efficiently fetching data based on data access patterns and adaptively configuring memory-centric and compute-centric cores. Additionally, SCRec integrates hardware acceleration cores to enhance DLRM computations, particularly allowing for the high-performance reconstruction of approximated embedding vectors from extremely compressed tensor-train (TT) format. By combining its software framework and hardware accelerators, while eliminating data communication overhead by being implemented on a single server, SCRec achieves substantial improvements in DLRM inference performance. It delivers up to 55.77 speedup compared to a CPU-DRAM system with no loss in accuracy and up to 13.35 energy efficiency gains over a multi-GPU system. I NTRODUCTION R RECOMMENDA TION systems are widely used in social network services and video streaming platforms to provide personalized and preferred content to consumers as described in Fig.1. They are also employed in search engines to offer differentiated search services [1]-[5]. For example, more than 80% of Meta's data center resources are allocated to recommendation system inference, while over 50% are utilized for training these systems [6]. Traditional recommendation systems relied on collaborative filtering techniques, such as content filtering using matrix factorization [7]-[10]. However, with advancements in deep neural networks (DNNs), deep learning recommendation models (DLRMs) that combine embedding tables (EMBs) and This work was supported by Samsung Electronics Co., Ltd.. Manuscript received MM dd, yyyy; revised MM dd, yyyy. These models are widely adopted in data centers, with recent focuses on both software-level and hardware-level optimizations [11]- [17]. This combination has demonstrated superior recommendation performance, making DLRM the industry standard in recommendation systems.

Cybersecurity researchers have issued an urgent warning as almost 1.5 million private photos from dating apps are exposed. Affected apps include the kink dating sites BDSM People and CHICA, as well as LGBT dating services PINK, BRISH, and TRANSLOVE - all of which were developed by M.A.D Mobile. The leaked files include photos used for verification, photos removed by app moderators, and photos sent in direct messages between users - many of which were explicit. These sensitive snaps were being stored online without password protection, meaning anyone with the link could view and download them. Researchers from Cybernews, who discovered the vulnerability, say this easily exploited security flaw put up to 900,000 users at risk of further hacks or extortion.

We propose Rec-R1, a general reinforcement learning framework that bridges large language models (LLMs) with recommendation systems through closed-loop optimization. Unlike prompting and supervised fine-tuning (SFT), Rec-R1 directly optimizes LLM generation using feedback from a fixed black-box recommendation model, without relying on synthetic SFT data from proprietary models such as GPT-4o. This avoids the substantial cost and effort required for data distillation. To verify the effectiveness of Rec-R1, we evaluate it on two representative tasks: product search and sequential recommendation. Experimental results demonstrate that Rec-R1 not only consistently outperforms prompting- and SFT-based methods, but also achieves significant gains over strong discriminative baselines, even when used with simple retrievers such as BM25. Moreover, Rec-R1 preserves the general-purpose capabilities of the LLM, unlike SFT, which often impairs instruction-following and reasoning. These findings suggest Rec-R1 as a promising foundation for continual task-specific adaptation without catastrophic forgetting.

Large language model-based agents are increasingly used in recommender systems (Agent4RSs) to achieve personalized behavior modeling. Specifically, Agent4RSs introduces memory mechanisms that enable the agents to autonomously learn and self-evolve from real-world interactions. However, to the best of our knowledge, how robust Agent4RSs are remains unexplored. As such, in this paper, we propose the first work to attack Agent4RSs by perturbing agents' memories, not only to uncover their limitations but also to enhance their security and robustness, ensuring the development of safer and more reliable AI agents. Given the security and privacy concerns, it is more practical to launch attacks under a black-box setting, where the accurate knowledge of the victim models cannot be easily obtained. Moreover, the practical attacks are often stealthy to maximize the impact. To this end, we propose a novel practical attack framework named DrunkAgent. DrunkAgent consists of a generation module, a strategy module, and a surrogate module. The generation module aims to produce effective and coherent adversarial textual triggers, which can be used to achieve attack objectives such as promoting the target items. The strategy module is designed to `get the target agents drunk' so that their memories cannot be effectively updated during the interaction process. As such, the triggers can play the best role. Both of the modules are optimized on the surrogate module to improve the transferability and imperceptibility of the attacks. By identifying and analyzing the vulnerabilities, our work provides critical insights that pave the way for building safer and more resilient Agent4RSs. Extensive experiments across various real-world datasets demonstrate the effectiveness of DrunkAgent.

Mr Nazarovas said the discovery of unprotected sensitive material comes with a significant risk for the platforms' users. Malicious hackers could have found the images and extorted individuals. There is also a risk to those who live in countries hostile to LGBT people. None of the text content of private messages was found to be stored in this way and the images are not labelled with user names or real names, which would make crafting targeted attacks at users more complex. In an email M.A.D Mobile said it was grateful to the researcher for uncovering the vulnerability in the apps to prevent a data breach from occurring.

Recommender systems operate in closed feedback loops, where user interactions reinforce popularity bias, leading to over-recommendation of already popular items while under-exposing niche or novel content. Existing bias mitigation methods, such as Inverse Propensity Scoring (IPS) and Off- Policy Correction (OPC), primarily operate at the ranking stage or during training, lacking explicit real-time control over exposure dynamics. In this work, we introduce an exposure- aware retrieval scoring approach, which explicitly models item exposure probability and adjusts retrieval-stage ranking at inference time. Unlike prior work, this method decouples exposure effects from engagement likelihood, enabling controlled trade-offs between fairness and engagement in large-scale recommendation platforms. We validate our approach through online A/B experiments in a real-world video recommendation system, demonstrating a 25% increase in uniquely retrieved items and a 40% reduction in the dominance of over-popular content, all while maintaining overall user engagement levels. Our results establish a scalable, deployable solution for mitigating popularity bias at the retrieval stage, offering a new paradigm for bias-aware personalization.