Hermes: Boosting the Performance of Machine-Learning-Based Intrusion Detection System through Geometric Feature Learning

C Zhang, S Shi, N Wang, X Xu, S Li, L Zheng… - Proceedings of the …, 2024 - dl.acm.org
Anomaly-Based Intrusion Detection Systems (IDSs) have been extensively researched for
their ability to detect zero-day attacks. These systems establish a baseline of normal …

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models

S Shi, MS Haque, A Parida, MG Linguraru… - arXiv preprint arXiv …, 2024 - arxiv.org
Federated learning (FL) allows a set of clients to collaboratively train a machine-learning
model without exposing local training samples. In this context, it is considered to be privacy …

Gradient Inversion of Text-Modal Data in Distributed Learning

Z Ye, W Luo, Q Zhou, Y Tang, Z Zhu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Gradient inversion attacks (GIAs) pose significant challenges to the privacy-preserving
paradigm of distributed learning. These attacks employ carefully designed strategies to …

Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning

S Sun, S Sugrim, A Stavrou, H Wang - arXiv preprint arXiv:2407.09958, 2024 - arxiv.org
Federated Learning (FL) exposes vulnerabilities to targeted poisoning attacks that aim to
cause misclassification specifically from the source class to the target class. However, using …

State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey

C Zhang - arXiv preprint arXiv:2404.16847, 2024 - arxiv.org
This paper examines the evolving landscape of machine learning (ML) and its profound
impact across various sectors, with a special focus on the emerging field of Privacy …

Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods

Z Zhang - arXiv preprint arXiv:2402.15617, 2024 - arxiv.org
Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to
make decisions based on real-world experiences. This approach has significantly advanced …

Machine Learning-Based Intrusion Detection Systems: Capabilities, Methodologies, and Open Research Challenges

C Zhang, N Wang, YT Hou, W Lou - Authorea Preprints - techrxiv.org
Intrusion Detection Systems (IDSs) are vital for protecting computer networks against
unauthorized access and evolving cyber threats. Traditional signature-based IDSs, while …