Desmp: Differential privacy-exploited stealthy model poisoning attacks in federated learning

MT Hossain, S Islam, S Badsha… - 2021 17th International …, 2021 - ieeexplore.ieee.org
Federated learning (FL) has become an emerging machine learning technique lately due to
its efficacy in safeguarding the client's confidential information. Nevertheless, despite the …

Brnes: Enabling security and privacy-aware experience sharing in multiagent robotic and autonomous systems

MT Hossain, HM La, S Badsha… - 2023 IEEE/RSJ …, 2023 - ieeexplore.ieee.org
Although experience sharing (ES) accelerates multiagent reinforcement learning (MARL) in
an advisor-advisee framework, attempts to apply ES to decentralized multiagent systems …

Rampart: Reinforcing autonomous multi-agent protection through adversarial resistance in transportation

MT Hossain, H La, S Badsha - Journal on Autonomous Transportation …, 2024 - dl.acm.org
In the field of multi-agent autonomous transportation, such as automated payload delivery or
highway on-ramp merging, agents routinely exchange knowledge to optimize their shared …

Differential privacy data release scheme using microaggregation with conditional feature selection

X Ye, Y Zhu, M Zhang, H Deng - IEEE Internet of Things Journal, 2023 - ieeexplore.ieee.org
Differential privacy (DP) has achieved great progress in addressing the user privacy
preservation issues related to data analysis in the Internet of Things (IoT) services and …

A resource allocation scheme for energy demand management in 6g-enabled smart grid

S Islam, I Zografopoulos, MT Hossain… - 2023 IEEE Power & …, 2023 - ieeexplore.ieee.org
Smart grid (SG) systems enhance grid resilience and efficient operation, leveraging the
bidirectional flow of energy and information between generation facilities and prosumers …

Hiding in plain sight: Differential privacy noise exploitation for evasion-resilient localized poisoning attacks in multiagent reinforcement learning

MT Hossain, H La - 2023 International Conference on Machine …, 2023 - ieeexplore.ieee.org
Lately, differential privacy (DP) has been introduced in cooperative multiagent reinforcement
learning (CMARL) to safe-guard the agents' privacy against adversarial inference during …

Privacy cost optimization of smart meters using URLLC and demand side energy trading

MB Hossain, SR Pokhrel, J Choi - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this article, we consider ultra-reliable low-latency communication (URLLC) for efficient
energy trading over a smart grid (SG) network using home-based smart meters (SM). We …

Adversarial analysis of the differentially-private federated learning in cyber-physical critical infrastructures

MT Hossain, S Badsha, H La, H Shen, S Islam… - arxiv preprint arxiv …, 2022 - arxiv.org
Federated Learning (FL) has become increasingly popular to perform data-driven analysis
in cyber-physical critical infrastructures. Since the FL process may involve the client's …

Preserving Smart Grid Integrity: A Differential Privacy Framework for Secure Detection of False Data Injection Attacks in the Smart Grid

N Ravi, A Scaglione, S Peisert, P Pradhan - arxiv preprint arxiv …, 2024 - arxiv.org
In this paper, we present a framework based on differential privacy (DP) for querying electric
power measurements to detect system anomalies or bad data caused by false data …