Real-time network intrusion detection via decision transformers

J Chen, H Zhou, Y Mei, G Adam, ND Bastian… - arxiv preprint arxiv …, 2023 - arxiv.org
Many cybersecurity problems that require real-time decision-making based on temporal
observations can be abstracted as a sequence modeling problem, eg, network intrusion …

Statistically efficient variance reduction with double policy estimation for off-policy evaluation in sequence-modeled reinforcement learning

H Zhou, T Lan, V Aggarwal - arxiv preprint arxiv:2308.14897, 2023 - arxiv.org
Offline reinforcement learning aims to utilize datasets of previously gathered environment-
action interaction records to learn a policy without access to the real environment. Recent …

A survey on the application of generative adversarial networks in cybersecurity: prospective, direction and open research scopes

MM Arifin, MS Ahmed, TK Ghosh, IA Udoy… - arxiv preprint arxiv …, 2024 - arxiv.org
With the proliferation of Artificial Intelligence, there has been a massive increase in the
amount of data required to be accumulated and disseminated digitally. As the data are …

Real-time network intrusion detection via importance sampled decision transformers

H Zhou, J Chen, Y Mei, G Adam… - 2024 IEEE 21st …, 2024 - ieeexplore.ieee.org
Many real-time cybersecurity problems, like network intrusion detection from packet
sequences, can be abstracted as sequence modeling issues. Traditional approaches such …

Double policy estimation for importance sampling in sequence modeling-based reinforcement learning

H Zhou, T Lan, V Aggarwal - NeurIPS 2023 Foundation Models for …, 2023 - openreview.net
Offline reinforcement learning aims to utilize datasets of previously gathered environment-
action interaction records to learn a policy without access to the real environment. Recent …

RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space

J Chen, H Zhou, Y Mei, C Joe-Wong, G Adam… - arxiv preprint arxiv …, 2024 - arxiv.org
Deep Reinforcement Learning (DRL) algorithms have achieved great success in solving
many challenging tasks while their black-box nature hinders interpretability and real-world …

Debiasing Machine Unlearning with Counterfactual Examples

Z Chen, J Wang, J Zhuang, AG Reddy… - arxiv preprint arxiv …, 2024 - arxiv.org
The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of
their historical actions by implementing machine-learning techniques. These techniques …

Multi-Memristor Based Distributed Decision Tree Circuit for Cybersecurity Applications

L Zhang, J Riem, J Chen, H Mackay… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Cybersecurity at the edge requires fast computing in energy-constrained environments.
Decision trees can provide an explainable solution for network intrusion detection with high …

Exploration, Collaboration, and Applications in Multi-Agent Reinforcement Learning

J Chen - ACM SIGMETRICS Performance Evaluation Review, 2025 - dl.acm.org
Research Summary: In recent years, the field of humancentric decision-making has
emerged as a critical area of research, driven by its potential to fundamentally reshape how …

Co-Design of Decision Trees for Network Intrusion Detection at the Edge on Digital vs. Analog Hardware

J Riem, L Zhang, J Chen, H Mackay… - MILCOM 2024-2024 …, 2024 - ieeexplore.ieee.org
Enabling cybersecurity at the network edge requires energy-efficient and lightweight
implementations of explainable network intrusion detection in constrained environments …