Junae Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Junae Kim has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Maxwell Standen
Defence Science and Technology
3 shared publications - Amardeep Kaur
Defence Science and Technology Group
2 shared publications - David Bowman
Defence Science and Technology
2 shared publications Abigail M.Y. Koay
1 shared publication- Ashlesha Akella
School of Computer Science, University of Technology Sydney, Ultimo, NSW 2007, Australia
1 shared publication - Callum Baillie
Department of Defence
1 shared publication
Latest Publications
- 1 October 2026
- Published by Springer Nature
- p. 243-261
Co-steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs
- 1 October 2026
- Published by Springer Nature
- p. 243-261
Co-steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs
- Open Access
- 8 January 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 167
Multi-agent reinforcement curriculum learning for real unmanned ground vehicles
- 8 January 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 167
Open AccessMulti-agent reinforcement curriculum learning for real unmanned ground vehicles
- Top Cited PapersOpen Access
- 24 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (5) , 1-35
Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning (AML) attacks. Execution-time AML attacks against MARL are complex due to effects that propagate across time and between agents. To understand the interaction between AML and MARL, this survey covers attacks and defences for MARL, Multi-Agent Learning (MAL), and Deep Reinforcement Learning (DRL). This survey proposes a novel perspective on AML attacks based on attack vectors. This survey also proposes a framework that addresses gaps in current modelling frameworks and enables the comparison of different attacks against MARL. Lastly, the survey identifies knowledge gaps and future avenues of research.
- 24 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (5) , 1-35
Top Cited PapersOpen AccessAdversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning (AML) attacks. Execution-time AML attacks against MARL are complex due to effects that propagate across time and between agents. To understand the interaction between AML and MARL, this survey covers attacks and defences for MARL, Multi-Agent Learning (MAL), and Deep Reinforcement Learning (DRL). This survey proposes a novel perspective on AML attacks based on attack vectors. This survey also proposes a framework that addresses gaps in current modelling frameworks and enables the comparison of different attacks against MARL. Lastly, the survey identifies knowledge gaps and future avenues of research.
- Open Access
A Survey on Adversarial Robustness of LiDAR-based Machine Learning Perception in Autonomous Vehicles
In autonomous driving, the combination of AI and vehicular technology offers great potential. However, this amalgamation comes with vulnerabilities to adversarial attacks. This survey focuses on the intersection of Adversarial Machine Learning (AML) and autonomous systems, with a specific focus on LiDAR-based systems. We comprehensively explore the threat landscape, encompassing cyber-attacks on sensors and adversarial perturbations. Additionally, we investigate defensive strategies employed in countering these threats. This paper endeavors to present a concise overview of the challenges and advances in securing autonomous driving systems against adversarial threats, emphasizing the need for robust defenses to ensure safety and security.
Open AccessA Survey on Adversarial Robustness of LiDAR-based Machine Learning Perception in Autonomous Vehicles
In autonomous driving, the combination of AI and vehicular technology offers great potential. However, this amalgamation comes with vulnerabilities to adversarial attacks. This survey focuses on the intersection of Adversarial Machine Learning (AML) and autonomous systems, with a specific focus on LiDAR-based systems. We comprehensively explore the threat landscape, encompassing cyber-attacks on sensors and adversarial perturbations. Additionally, we investigate defensive strategies employed in countering these threats. This paper endeavors to present a concise overview of the challenges and advances in securing autonomous driving systems against adversarial threats, emphasizing the need for robust defenses to ensure safety and security.
- 2 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 13963-13978
Decentralized Coordination for Multi-Agent Data Collection in Dynamic Environments
Coordinated multi-robot systems are an effective way to harvest data from sensor networks and implement active perception strategies. However, achieving efficient coordination in a way that guarantees a target QoS while adapting dynamically to changes (in the environment and/or in the system) is a key open issue. In this paper, we propose a novel decentralized Monte Carlo Tree Search (MCTS) algorithm for dynamic environments that allows agents to optimize their own actions while achieving some form of coordination. Its main underlying idea is to balance adaptively the exploration-exploitation trade-off to deal effectively with changes in the environment while filtering out outdated and irrelevant samples via a sliding window mechanism. We show both theoretically and through simulations that in dynamic environments our algorithm provides a log-factor (in terms of time steps) smaller regret than state-of-the-art decentralized multi-agent planning methods. We instantiate our approach to the problem of underwater data collection, showing in a variety of different settings that our approach greatly outperforms the best-competing approaches, both in terms of convergence speed and global utility.
- 2 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 13963-13978
Decentralized Coordination for Multi-Agent Data Collection in Dynamic Environments
Coordinated multi-robot systems are an effective way to harvest data from sensor networks and implement active perception strategies. However, achieving efficient coordination in a way that guarantees a target QoS while adapting dynamically to changes (in the environment and/or in the system) is a key open issue. In this paper, we propose a novel decentralized Monte Carlo Tree Search (MCTS) algorithm for dynamic environments that allows agents to optimize their own actions while achieving some form of coordination. Its main underlying idea is to balance adaptively the exploration-exploitation trade-off to deal effectively with changes in the environment while filtering out outdated and irrelevant samples via a sliding window mechanism. We show both theoretically and through simulations that in dynamic environments our algorithm provides a log-factor (in terms of time steps) smaller regret than state-of-the-art decentralized multi-agent planning methods. We instantiate our approach to the problem of underwater data collection, showing in a variety of different settings that our approach greatly outperforms the best-competing approaches, both in terms of convergence speed and global utility.
- 27 May 2023
- Published by Springer Nature
- p. 147-158
Leveraging Generative Models for Combating Adversarial Attacks on Tabular Datasets
- 27 May 2023
- Published by Springer Nature
- p. 147-158
Leveraging Generative Models for Combating Adversarial Attacks on Tabular Datasets
- Open Access
- 7 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11265
Cascaded Reinforcement Learning Agents for Large Action Spaces in Autonomous Penetration Testing
Organised attacks on a computer system to test existing defences, i.e., penetration testing, have been used extensively to evaluate network security. However, penetration testing is a time-consuming process. Additionally, establishing a strategy that resembles a real cyber-attack typically requires in-depth knowledge of the cybersecurity domain. This paper presents a novel architecture, named deep cascaded reinforcement learning agents, or CRLA, that addresses large discrete action spaces in an autonomous penetration testing simulator, where the number of actions exponentially increases with the complexity of the designed cybersecurity network. Employing an algebraic action decomposition strategy, CRLA is shown to find the optimal attack policy in scenarios with large action spaces faster and more stably than a conventional deep Q-learning agent, which is commonly used as a method for applying artificial intelligence to autonomous penetration testing.
- 7 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11265
Open AccessCascaded Reinforcement Learning Agents for Large Action Spaces in Autonomous Penetration Testing
Organised attacks on a computer system to test existing defences, i.e., penetration testing, have been used extensively to evaluate network security. However, penetration testing is a time-consuming process. Additionally, establishing a strategy that resembles a real cyber-attack typically requires in-depth knowledge of the cybersecurity domain. This paper presents a novel architecture, named deep cascaded reinforcement learning agents, or CRLA, that addresses large discrete action spaces in an autonomous penetration testing simulator, where the number of actions exponentially increases with the complexity of the designed cybersecurity network. Employing an algebraic action decomposition strategy, CRLA is shown to find the optimal attack policy in scenarios with large action spaces faster and more stably than a conventional deep Q-learning agent, which is commonly used as a method for applying artificial intelligence to autonomous penetration testing.
- Open Access
CybORG: An Autonomous Cyber Operations Research Gym
Autonomous Cyber Operations (ACO) involves the consideration of blue team (defender) and red team (attacker) decision-making models in adversarial scenarios. To support the application of machine learning algorithms to solve this problem, and to encourage such practitioners to attend to problems in the ACO setting, a suitable gym (toolkit for experiments) is necessary. We introduce CybORG, a work-in-progress gym for ACO research. Driven by the need to efficiently support reinforcement learning to train adversarial decision-making models through simulation and emulation, our design differs from prior related work. Our early evaluation provides some evidence that CybORG is appropriate for our purpose and may provide a basis for advancing ACO research towards practical applications.
Open AccessCybORG: An Autonomous Cyber Operations Research Gym
Autonomous Cyber Operations (ACO) involves the consideration of blue team (defender) and red team (attacker) decision-making models in adversarial scenarios. To support the application of machine learning algorithms to solve this problem, and to encourage such practitioners to attend to problems in the ACO setting, a suitable gym (toolkit for experiments) is necessary. We introduce CybORG, a work-in-progress gym for ACO research. Driven by the need to efficiently support reinforcement learning to train adversarial decision-making models through simulation and emulation, our design differs from prior related work. Our early evaluation provides some evidence that CybORG is appropriate for our purpose and may provide a basis for advancing ACO research towards practical applications.
- 9 September 2019
- Published by Springer Nature
- p. 731-746
Towards Attention Based Vulnerability Discovery Using Source Code Representation
- 9 September 2019
- Published by Springer Nature
- p. 731-746
Towards Attention Based Vulnerability Discovery Using Source Code Representation