ALYCON-Threat-Landscape

ALYCON：高级威胁图景分析 使用信息论相空间分析的多域威胁检测 概述 ALYCON 相空间可视化，展示多域威胁检测与异常分类。 框架： 无训练、通用异常检测，使用香农熵（H）、费舍尔信息（F）和瓦瑟斯坦距离（W）将系统状态映射到几何上不同的区域。 可视化组件 威胁图景地图显示： 相空间坐标： H, F, W 检测轴 状态聚类： 正常与异常状态 多域分析： 跨域威胁检测能力 实时检测： 基于几何分离的警报 联系方式 Michael Castens 通过 GitHub issues 联系 主仓库： ALYCON 框架 许可证： 保留所有权利。许可事宜请联系作者。...

Deep Learning-Driven Friendly Jamming for Secure Multicarrier ISAC under Channel Uncertainty

Integrated sensing and communication ISAC systems promise efficient spectrum utilization by jointly supporting radar sensing and wireless communication. This paper presents a deep learning-driven framework for enhancing physical-layer security in multicarrier ISAC systems under imperfect channel...

Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection

Software vulnerability detection is a critical task for securing software systems and can be formulated as a binary classification problem: given a code snippet, determine whether it contains a vulnerability. Existing multimodal approaches typically fuse Natural Code Sequence NCS representations...

SelectiveShield: Lightweight Hybrid Defense against Gradient Leakage in Federated Learning

Federated Learning FL enables collaborative model training on decentralized data but remains vulnerable to gradient leakage attacks that can reconstruct sensitive user information. Existing defense mechanisms, such as differential privacy DP and homomorphic encryption HE, often introduce a...

ModShift: Model Privacy Via Designed Shifts

In this paper, shifts are introduced to preserve model privacy against an eavesdropper in federated learning. Model learning is treated as a parameter estimation problem. This perspective allows us to derive the Fisher Information matrix of the model updates from the shifted updates and drive the...

Unlearning Isn'T Deletion: Investigating Reversibility of Machine Unlearning in LLMs

Unlearning in large language models LLMs is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can be misleading: models often appear to forget, but their original behavior can ...