arXiv subjects

Zain ul Abdeen

Publications and source records attributed to Zain ul Abdeen.

7 recordsLinked to original sources

arXiv2026

Parameter Stress Analysis in Reinforcement Learning: Applying Synaptic Filtering to Policy Networks

This paper explores reinforcement learning (RL) policy robustness by systematically analyzing network parameters under internal and external stresses. \textcolor{black}{We apply synaptic filtering methods using high-pass, low-pass, and pulse-wave filters from} \citep{pravin2024fragility}, as an internal stress by selectively perturbing parameters, while adversarial attacks apply external stress through modified agent observations. This dual approach enables the classification of parameters as \textit{fragile}, \textit{robust}, or \textit{antifragile}, based on their influence on policy performance in clean and adversarial settings. Parameter scores are defined to quantify these characteristics, and the framework is validated on proximal policy optimization (PPO)-trained agents in Mujoco continuous control environments. The results highlight the presence of antifragile parameters that enhance policy performance under stress, demonstrating the potential of targeted filtering techniques to improve RL policy adaptability. These insights provide a foundation for future advancements in the design of robust and antifragile RL systems.

cs.LG↗

arXiv2026

Toward Adaptive Grid Resilience: A Gradient-Free Meta-RL Framework for Critical Load Restoration

Restoring critical loads after extreme events demands adaptive control to maintain distribution-grid resilience, yet uncertainty in renewable generation, limited dispatchable resources, and nonlinear dynamics make effective restoration difficult. Reinforcement learning (RL) can optimize sequential decisions under uncertainty, but standard RL often generalizes poorly and requires extensive retraining for new outage configurations or generation patterns. We propose a meta-guided gradient-free RL (MGF-RL) framework that learns a transferable initialization from historical outage experiences and rapidly adapts to unseen scenarios with minimal task-specific tuning. MGF-RL couples first-order meta-learning with evolutionary strategies, enabling scalable policy search without gradient computation while accommodating nonlinear, constrained distribution-system dynamics. Experiments on IEEE 13-bus and IEEE 123-bus test systems show that MGF-RL outperforms standard RL, MAML-based meta-RL, and model predictive control across reliability, restoration speed, and adaptation efficiency under renewable forecast errors. MGF-RL generalizes to unseen outages and renewable patterns while requiring substantially fewer fine-tuning episodes than conventional RL. We also provide sublinear regret bounds that relate adaptation efficiency to task similarity and environmental variation, supporting the empirical gains and motivating MGF-RL for real-time load restoration in renewable-rich distribution grids.

cs.LG↗

arXiv2025

Cloud Revolution: Tracing the Origins and Rise of Cloud Computing

The history behind the development of cloud computing is more than several decades of technological progress in the fields of virtualization, distributed systems, and high-speed networking, but its current application is much broader than the underlying technologies that made it possible. This paper reexamines the historical evolution of the field, including the initial ideas of resource sharing and utility-based computing approaches and the development of hyperscale data centers and modern globally federated cloud ecosystems. We also analyze the technological and economic forces and point to the way cloud platforms altered the organizational computing habits, decreasing the entrance-level to the data-intensive and computation-heavy apps. The study also takes into account the ongoing limitations which have come with the large-scale adoption of clouds which include exposure to security due to the weaknesses in configuration, particular establishment regulations, and structural reliance on the single vendors. Lastly, we address some of the new trends that are transforming the cloud environment, including the convergence of edge and cloud infrastructure, the increased prominence of AI-optimised architectures and the initial adoption of quantum computing services. Collectively, the developments above describe an emerging but quickly changing paradigm with its future direction being determined by a strike of balancing between scalability, openness, and trust.

cs.DC↗

arXiv2025

A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks

Certified robustness is a critical property for deploying neural networks (NN) in safety-critical applications. A principle approach to achieving such guarantees is to constrain the global Lipschitz constant of the network. However, accurate methods for Lipschitz-constrained training often suffer from non-convex formulations and poor scalability due to reliance on global semidefinite programs (SDPs). In this letter, we propose a convex training framework that enforces global Lipschitz constraints via semidefinite relaxation. By reparameterizing the NN using loop transformation, we derive a convex admissibility condition that enables tractable and certifiable training. While the resulting formulation guarantees robustness, its scalability is limited by the size of global SDP. To overcome this, we develop a randomized subspace linear matrix inequalities (RS-LMI) approach that decomposes the global constraints into sketched layerwise constraints projected onto low-dimensional subspaces, yielding a smooth and memory-efficient training objective. Empirical results on MNIST, CIFAR-10, and ImageNet demonstrate that the proposed framework achieves competitive accuracy with significantly improved Lipschitz bounds and runtime performance.

cs.LG↗

arXiv2024

IP-FL: Incentivized and Personalized Federated Learning

Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary incentives such as personalized model appeal for clients. In this paper, we first propose to treat incentivization and personalization as interrelated challenges and solve them with an incentive mechanism that fosters personalized learning. Additionally, current methods depend on an aggregator for client clustering, which is limited by a lack of access to clients' confidential information due to privacy constraints, leading to inaccurate clustering. To overcome this, we propose direct client involvement, allowing clients to indicate their cluster membership preferences based on data distribution and incentive-driven feedback. Our approach enhances the personalized model appeal for self-aware clients with high-quality data leading to their active and consistent participation. Our evaluation demonstrates significant improvements in test accuracy (8-45%), personalized model appeal (3-38%), and participation rates (31-100%) over existing FL models, including those addressing data heterogeneity and personalization.

cs.LG↗

arXiv2024

Defense against Joint Poison and Evasion Attacks: A Case Study of DERMS

There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact operational reliability. While a data-driven intrusion detection system (IDS) can potentially thwart attacks during deployment, also known as the evasion attack, the training of the detection algorithm may be corrupted by adversarial data injected into the database, also known as the poisoning attack. In this paper, we propose the first framework of IDS that is robust against joint poisoning and evasion attacks. We formulate the defense mechanism as a bilevel optimization, where the inner and outer levels deal with attacks that occur during training time and testing time, respectively. We verify the robustness of our method on the IEEE-13 bus feeder model against a diverse set of poisoning and evasion attack scenarios. The results indicate that our proposed method outperforms the baseline technique in terms of accuracy, precision, and recall for intrusion detection.

cs.CR↗

arXiv2022

Learning Neural Networks under Input-Output Specifications

In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors. Our strategy is to find an inner approximation of the set of admissible policy parameters, which is convex in a transformed space. To this end, we address the key technical challenge of convexifying the verification condition for neural networks, which is derived by abstracting the nonlinear specifications and activation functions with quadratic constraints. In particular, we propose a reparametrization scheme of the original neural network based on loop transformation, which leads to a convex condition that can be enforced during learning. This theoretical construction is validated in an experiment that specifies reachable sets for different regions of inputs.

eess.SY↗