Data privacy labels are a great idea for mobile apps, but the current versions just aren’t good enough.
Apple Breaks Precedent, Patches DarkSword for iOS 18
Even organizations with users unwilling or unable to adopt iOS 26 can now protect themselves from a severe mobile OS-cracking tool.
Blast Radius of TeamPCP Attacks Expands Amid Hacker Infighting
As organizations disclose breaches tied to TeamPCP’s supply chain attacks, ShinyHunters and Lapsus$ are getting involved, taking credit, and creating a murky situation for enterprises.
Picking Up ‘Skull Vibrations’? Could Be XR Headset Authentication
“Skull vibration harmonics generated by vital signs” can be used to sign in to VR, AR, and MR headsets, according to emerging research.
Source Code Leaks Highlight Lack of Supply Chain Oversight
Or, why the software supply chain should be treated as critical infrastructure with guardrails built in at every layer.
Chainguard Unveils Factory 2.0 to Automate Hardening the Software Supply Chain
The rebuilt Chainguard platform adds deeper security designed to continuously reconcile open-source artifacts across containers, libraries, Actions and skills.
CrowdStrike Next-Gen SIEM Can Now Ingest Microsoft Defender Telemetry
Once CrowdStrike’s nemesis, Microsoft is now a collaborator. A shared interest in Formula 1 helped thaw the years-long fierce rivalry.
US pharma tariffs of up to 100% finalised by Trump
Trump signs his pharma tariffs executive order, which won’t affect most large pharma groups but could deal a hefty blow to smaller companies.
Physics-Informed Transformer for Multi-Band Channel Frequency Response Reconstruction
arXiv:2604.01944v1 Announce Type: cross Abstract: Wideband channel frequency response (CFR) estimation is challenging in multi-band wireless systems, especially when one or more sub-bands are temporarily blocked by co-channel interference. We present a physics-informed complex Transformer that reconstructs the full wideband CFR from such fragmented, partially observed spectrum snapshots. The interference pattern in each sub-band is […]
The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level
arXiv:2604.02178v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency, it remains an open question whether their sparsity makes them inherently easier to interpret than dense feed-forward networks (FFNs). […]
TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
arXiv:2508.17519v2 Announce Type: replace-cross Abstract: Handling missing data in time series classification remains a significant challenge in various domains. Traditional methods often rely on imputation, which may introduce bias or fail to capture the underlying temporal dynamics. In this paper, we propose TANDEM (Temporal Attention-guided Neural Differential Equations for Missingness), an attention-guided neural differential equation […]
Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy
arXiv:2604.01705v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) is a critical interface for human-AI interaction in gastrointestinal endoscopy, yet its reliability in real-world clinical settings is limited by domain-specific terminology and complex acoustic conditions. Here, we present EndoASR, a domain-adapted ASR system designed for real-time deployment in endoscopic workflows. We develop a two-stage adaptation […]