-
Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
arXiv:2508.09201v5 Announce Type: replace Abstract: Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and accuracy. While learning-based methods trained…Read more
Published: 5 hours ago | Source: cs.CR updates on arXiv.org
-
Theoretically Principled Federated Learning for Balancing Privacy and Utility
arXiv:2305.15148v3 Announce Type: replace-cross Abstract: We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy measurements that maps…Read more
Published: 5 hours ago | Source: cs.CR updates on arXiv.org
-
A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots
arXiv:2606.19660v2 Announce Type: replace Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at isolated pipeline stages and remain incomplete. Input…Read more
Published: 5 hours ago | Source: cs.CR updates on arXiv.org
-
Clinically Grounded Privacy Evaluation of Medical LMs
arXiv:2606.09590v3 Announce Type: replace-cross Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under realistic threat models. We introduce a clinically grounded framework that…Read more
Published: 5 hours ago | Source: cs.CR updates on arXiv.org
-
AirMoE: Realizing Over-the-Air Distributed Mixture-of-Experts Inference at the Wireless Edge
arXiv:2608.22932v2 Announce Type: replace Abstract: Mixture-of-experts (MoE) architectures enable efficient large language model (LLM) inference at the wireless edge through sparse activation. The wireless distributed MoE (WIDE) architecture addresses edge-resource constraints by distributing experts across devices coordinated by an edge…Read more
Published: 5 hours ago | Source: eess.SP updates on arXiv.org
-
Maximum-Volume Nonnegative Matrix Factorization
arXiv:2602.04795v3 Announce Type: replace-cross Abstract: Nonnegative matrix factorization (NMF) is a popular data embedding technique. Given a nonnegative data matrix $X$, it aims at finding two lower dimensional matrices, $W$ and $H$, such that $Xapprox WH$, where the factors $W$…Read more
Published: 5 hours ago | Source: eess.SP updates on arXiv.org
-
MI-SLAM: Magnetic Inertial SLAM Systems
arXiv:2512.10128v4 Announce Type: replace-cross Abstract: Spatially inhomogeneous magnetic fields offer a valuable, non-visual information source for positioning. Among systems leveraging this, magnetic field-based simultaneous localization and mapping (SLAM) systems are particularly attractive. These systems execute positioning and magnetic field mapping…Read more
Published: 5 hours ago | Source: eess.SP updates on arXiv.org
-
arXiv:2608.25393v1 Announce Type: new Abstract: Millimeter-wave (mmWave) multi-user MIMO systems are highly susceptible to dynamic blockages, and reconfigurable intelligent surfaces (RIS) have been introduced as a remedy. However, RIS links can themselves be blocked, while existing studies often assume ideal…Read more
Published: 5 hours ago | Source: eess.SP updates on arXiv.org
-
TeRFS: Temporal-Evolving Radio Field Synthesis
arXiv:2605.02359v2 Announce Type: replace Abstract: While radio-frequency (RF) field synthesis is fundamental to wireless networking, current approaches remain constrained by static assumptions, leaving them unable to track the rapid multipath reorganization of dynamic scenes. Modeling these transitions requires addressing two…Read more
Published: 5 hours ago | Source: eess.SP updates on arXiv.org
-
Coinbase, Better Open Bitcoin Mortgages After $260M Waitlist Demand
Qualified homebuyers can cover their cash down payment by borrowing against bitcoin instead of selling it, keeping the main mortgage a standard Fannie Mae loan. Coinbase One members can also receive up to $10,000 in closing-cost credits. Token-Backed Mortgage Reaches…Read more
Published: 6 hours ago | Source: Bitcoin News















