Adversarial Robustness on Image Classification with $k$-means

no code implementations • 15 Dec 2023 • Rollin Omari, Junae Kim, Paul Montague

In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations.

Adversarial Robustness Classification +2

SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning

no code implementations • 11 Jan 2023 • Maxwell Standen, Junae Kim, Claudia Szabo

Multi-Agent Reinforcement Learning (MARL) is vulnerable to Adversarial Machine Learning (AML) attacks and needs adequate defences before it can be used in real world applications.

Multi-agent Reinforcement Learning reinforcement-learning +1

Deep hierarchical reinforcement agents for automated penetration testing

no code implementations • 14 Sep 2021 • Khuong Tran, Ashlesha Akella, Maxwell Standen, Junae Kim, David Bowman, Toby Richer, Chin-Teng Lin

Penetration testing the organised attack of a computer system in order to test existing defences has been used extensively to evaluate network security.

Q-Learning

Positive Semidefinite Metric Learning with Boosting

no code implementations • NeurIPS 2009 • Chunhua Shen, Junae Kim, Lei Wang, Anton Hengel

In this work, we propose a boosting-based technique, termed BoostMetric, for learning a Mahalanobis distance metric.

General Classification Metric Learning