arXiv:2604.16969v1 Announce Type: new Abstract: Unmixing reveals the spatial distribution and spectral details of different constituents, called endmembers, in a hyperspectral image. Because unmixing has limited ground truth requirements, can accommodate mixed pixels, and is closely tied to light propagation, it is a uniquely powerful tool for analyzing hyperspectral images. However, spectral variability inhibits unmixing performance, the proper way to determine the number of endmembers is ambiguous, and the clarity of the endmembers degrades as more are included. […]

Ver mais

arXiv:2601.10740v1 Announce Type: new Abstract: Modern neural networks rely on generic activation functions (ReLU, GELU, SiLU) that ignore the mathematical structure inherent in scientific data. We propose Neuro-Symbolic Activation Discovery, a framework that uses Genetic Programming to extract interpretable mathematical formulas from data and inject them as custom activation functions. Our key contribution is the discovery of a Geometric Transfer phenomenon: activation functions learned from particle physics data successfully generalize to ecological classification, outperforming standard activations (ReLU, GELU, […]

Ver mais

Graph neural networks (GNNs) are designed to use attributed graphs to learn representations. Such representations are beneficial in the unsupervised learning of clusters and community detection. Nonetheless, such inference may reveal sensitive groups, clustered systems, or collective behaviors, raising concerns regarding group-level privacy. Community attribution in social and critical infrastructure networks, for example, can expose coordinated asset groups, operational hierarchies, and system dependencies that could be used for profiling or intelligence gathering. We study a defensive setting in […]

Ver mais

There’s a post-mortem template that’s become so familiar in Web3 it’s almost comforting. Bear market. Liquidity dried up. The team is moving on to pursue other opportunities. Thank you for being part of this journey. It’s usually true, in the way that “heart failure” is a true cause of death. It tells you nothing about why. After watching a lot of Web3 projects come apart, some slowly and some overnight, I’ve landed on a cause that almost never […]

Ver mais

On March 31, 2026, two research papers dropped on the same day and rewrote everything we thought we knew about Bitcoin’s quantum timeline. Google’s Quantum AI team, alongside researchers from Stanford and the Ethereum Foundation, published findings showing that breaking Bitcoin’s ECDSA encryption could require fewer than 500,000 physical qubits — a roughly 20-fold reduction from prior estimates that hovered in the millions. The same day, a Caltech/Oratomic paper demonstrated that neutral-atom architectures could push that number even […]

Ver mais

Federated learning (FL) enables collaborative model training without sharing raw data in edge environments, but is constrained by limited communication bandwidth and heterogeneous client data distributions. Prototype-based FL mitigates this issue by exchanging class-wise feature prototypes instead of full model parameters; however, existing methods still suffer from suboptimal generalization under severe communication constraints. In this paper, we propose RefProtoFL, a communication-efficient FL framework that integrates External-Referenced Prototype Alignment (ERPA) for representation consistency with Adaptive Probabilistic Update Dropping (APUD) […]

Ver mais

Despite legal mandates for the right to be forgotten, AI operators routinely fail to comply with data deletion requests. While machine unlearning (MU) provides a technical solution to remove personal data’s influence from trained models, ensuring compliance remains challenging due to the fundamental gap between MU’s technical feasibility and regulatory implementation. In this paper, we introduce the first economic framework for auditing MU compliance, by integrating certified unlearning theory with regulatory enforcement. We first characterize MU’s inherent verification […]

Ver mais

arXiv:2601.08044v1 Announce Type: new Abstract: Denial-of-Service (DoS) attacks pose a critical threat to Internet of Things (IoT) ecosystems, yet deploying effective intrusion detection on resource-constrained edge devices remains challenging. Kolmogorov-Arnold Networks (KANs) offer a compact alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate spline functions on edges rather than fixed activations on nodes, achieving competitive accuracy with fewer parameters. However, runtime B-spline evaluation introduces significant computational overhead unsuitable for latency-critical IoT applications. We propose a lookup table […]

Ver mais