IEEE

Frequency-Informed Encoder-Decoder Models with Expressivity for Time Series Anomaly Detection

Abstract: Improving anomaly detection accuracy in time series data is essential for the operation of communication networks. Encoder-decoder models, which learn the correlations within the data, have ...
IEEE

DTSF-CDNet: A Dual-Branch Encoder-Decoder Network with Differential Transformer Skip Fusion ...

Abstract: Change detection plays a vital role in numerous real-world domains, aiming to accurately identify regions that have changed between two temporally distinct images. Capturing the complex ...
GitHub

PULSE Protocol - Python Implementation

PULSE enables any AI system to communicate with any other AI system - regardless of vendor, framework, or architecture. The Problem: Enterprises deploy 15-30 different AI systems that cannot ...
GitHub

subinium/mpl-rust-backend

Replaces matplotlib's C++ Agg rasterizer with a Rust pipeline built on tiny-skia (CPU rasterizer) and FreeType text-as-paths. Supports PNG and SVG output with pixel-accurate fidelity across 26 tested ...

基于多模态感知与行为分析的二维码钓鱼防御机制研究

在数字化转型的浪潮中，电子邮件系统作为企业内外部信息交互的枢纽，始终是网络攻防博弈的主战场。长期以来，针对邮件系统的攻击主要集中于文本内容的混淆、恶意附件的伪装以及URL链接的隐匿。为了应对这些威胁，企业普遍部署了基于签名库、启发式规则及沙箱技术的邮件安全网关（SEG），形成了相对成熟的防御体系。然而，攻击者的战术始终随着防御技术的升级而动态演进。近年来，一种利用二维码作为攻击媒介的新型钓鱼手法— ...