arXiv subjects

Erchin Serpedin

Publications and source records attributed to Erchin Serpedin.

At least 55 records · Page 3Linked to original sources

arXiv2025

SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for detecting and mitigating hallucinations by leveraging Sparse Autoencoders (SAEs). While hallucination detection techniques and SAEs have been explored independently, their synergistic application in a comprehensive system, particularly for hallucination-aware query enrichment, has not been fully investigated. To validate the effectiveness of SAFE, we evaluate it on two models with available SAEs across three diverse cross-domain datasets designed to assess hallucination problems. Empirical results demonstrate that SAFE consistently improves query generation accuracy and mitigates hallucinations across all datasets, achieving accuracy improvements of up to 29.45%.

cs.CL↗

arXiv2023

CleftGAN: Adapting A Style-Based Generative Adversarial Network To Create Images Depicting Cleft Lip Deformity

A major obstacle when attempting to train a machine learning system to evaluate facial clefts is the scarcity of large datasets of high-quality, ethics board-approved patient images. In response, we have built a deep learning-based cleft lip generator designed to produce an almost unlimited number of artificial images exhibiting high-fidelity facsimiles of cleft lip with wide variation. We undertook a transfer learning protocol testing different versions of StyleGAN-ADA (a generative adversarial network image generator incorporating adaptive data augmentation (ADA)) as the base model. Training images depicting a variety of cleft deformities were pre-processed to adjust for rotation, scaling, color adjustment and background blurring. The ADA modification of the primary algorithm permitted construction of our new generative model while requiring input of a relatively small number of training images. Adversarial training was carried out using 514 unique frontal photographs of cleft-affected faces to adapt a pre-trained model based on 70,000 normal faces. The Frechet Inception Distance (FID) was used to measure the similarity of the newly generated facial images to the cleft training dataset, while Perceptual Path Length (PPL) and the novel Divergence Index of Severity Histograms (DISH) measures were also used to assess the performance of the image generator that we dub CleftGAN. We found that StyleGAN3 with translation invariance (StyleGAN3-t) performed optimally as a base model. Generated images achieved a low FID reflecting a close similarity to our training input dataset of genuine cleft images. Low PPL and DISH measures reflected a smooth and semantically valid interpolation of images through the transfer learning process and a similar distribution of severity in the training and generated images, respectively.

cs.CV↗

arXiv2023

Federated Learning Based Distributed Localization of False Data Injection Attacks on Smart Grids

Data analysis and monitoring on smart grids are jeopardized by attacks on cyber-physical systems. False data injection attack (FDIA) is one of the classes of those attacks that target the smart measurement devices by injecting malicious data. The employment of machine learning techniques in the detection and localization of FDIA is proven to provide effective results. Training of such models requires centralized processing of sensitive user data that may not be plausible in a practical scenario. By employing federated learning for the detection of FDIA attacks, it is possible to train a model for the detection and localization of the attacks while preserving the privacy of sensitive user data. However, federated learning introduces new problems such as the personalization of the detectors in each node. In this paper, we propose a federated learning-based scheme combined with a hybrid deep neural network architecture that exploits the local correlations between the connected power buses by employing graph neural networks as well as the temporal patterns in the data by using LSTM layers. The proposed mechanism offers flexible and efficient training of an FDIA detector in a distributed setup while preserving the privacy of the clients. We validate the proposed architecture by extensive simulations on the IEEE 57, 118, and 300 bus systems and real electricity load data.

cs.LG↗

arXiv2022

Unsupervised Anomaly Appraisal of Cleft Faces Using a StyleGAN2-based Model Adaptation Technique

This paper presents a novel machine learning framework to consistently detect, localize and rate congenital cleft lip anomalies in human faces. The goal is to provide a universal, objective measure of facial differences and reconstructive surgical outcomes that matches human judgments. The proposed method employs the StyleGAN2 generative adversarial network with model adaptation to produce normalized transformations of cleft-affected faces in order to allow for subsequent measurement of deformity using a pixel-wise subtraction approach. The complete pipeline of the proposed framework consists of the following steps: image preprocessing, face normalization, color transformation, morphological erosion, heat-map generation and abnormality scoring. Heatmaps that finely discern anatomic anomalies are proposed by exploiting the features of the considered framework. The proposed framework is validated through computer simulations and surveys containing human ratings. The anomaly scores yielded by the proposed computer model correlate closely with the human ratings of facial differences, leading to 0.942 Pearson's r score.

cs.CV↗

arXiv2022

Multi-Task and Transfer Learning for Federated Learning Applications

Federated learning enables many applications benefiting distributed and private datasets of a large number of potential data-holding clients. However, different clients usually have their own particular objectives in terms of the tasks to be learned from the data. So, supporting federated learning with meta-learning tools such as multi-task learning and transfer learning will help enlarge the set of potential applications of federated learning by letting clients of different but related tasks share task-agnostic models that can be then further updated and tailored by each individual client for its particular task. In a federated multi-task learning problem, the trained deep neural network model should be fine-tuned for the respective objective of each client while sharing some parameters for more generalizability. We propose to train a deep neural network model with more generalized layers closer to the input and more personalized layers to the output. We achieve that by introducing layer types such as pre-trained, common, task-specific, and personal layers. We provide simulation results to highlight particular scenarios in which meta-learning-based federated learning proves to be useful.

cs.LG↗

arXiv2022

Infinite Impulse Response Graph Neural Networks for Cyberattack Localization in Smart Grids

This study employs Infinite Impulse Response (IIR) Graph Neural Networks (GNN) to efficiently model the inherent graph network structure of the smart grid data to address the cyberattack localization problem. First, we numerically analyze the empirical frequency response of the Finite Impulse Response (FIR) and IIR graph filters (GFs) to approximate an ideal spectral response. We show that, for the same filter order, IIR GFs provide a better approximation to the desired spectral response and they also present the same level of approximation to a lower order GF due to their rational type filter response. Second, we propose an IIR GNN model to efficiently predict the presence of cyberattacks at the bus level. Finally, we evaluate the model under various cyberattacks at both sample-wise (SW) and bus-wise (BW) level, and compare the results with the existing architectures. It is experimentally verified that the proposed model outperforms the state-of-the-art FIR GNN model by 9.2% and 14% in terms of SW and BW localization, respectively.

eess.SP↗

arXiv2022

Clustered Scheduling and Communication Pipelining For Efficient Resource Management Of Wireless Federated Learning

This paper proposes using communication pipelining to enhance the wireless spectrum utilization efficiency and convergence speed of federated learning in mobile edge computing applications. Due to limited wireless sub-channels, a subset of the total clients is scheduled in each iteration of federated learning algorithms. On the other hand, the scheduled clients wait for the slowest client to finish its computation. We propose to first cluster the clients based on the time they need per iteration to compute the local gradients of the federated learning model. Then, we schedule a mixture of clients from all clusters to send their local updates in a pipelined manner. In this way, instead of just waiting for the slower clients to finish their computation, more clients can participate in each iteration. While the time duration of a single iteration does not change, the proposed method can significantly reduce the number of required iterations to achieve a target accuracy. We provide a generic formulation for optimal client clustering under different settings, and we analytically derive an efficient algorithm for obtaining the optimal solution. We also provide numerical results to demonstrate the gains of the proposed method for different datasets and deep learning architectures.

cs.LG↗

arXiv2022

Spatio-Temporal Failure Propagation in Cyber-Physical Power Systems

Cascading failure in power systems is triggered by a small perturbation that leads to a sequence of failures spread through the system. The interconnection between different components in a power system causes failures to easily propagate across the system. The situation gets worse by considering the interconnection between cyber and physical layers in power systems. A plethora of work has studied the cascading failure in power systems to calculate its impact on the system. Understanding how failures propagate into the system in time and space can help the system operator to take preventive actions and upgrade the system accordingly. Due to the nonlinearity of the power flow equation as well as the engineering constraints in the power system, it is essential to understand the spatio-temporal failure propagation in cyber-physical power systems (CPPS). This paper proposes an asynchronous algorithm for investigating failure propagation in CPPS. The physics of the power system is addressed by the full AC power flow equations. Various practical constraints including load shedding, load-generation balance, and island operation are considered to address practical constraints in power system operation. The propagation of various random initial attacks of different sizes is analyzed and visualized to elaborate on the applicability of the proposed approach. Our findings shed light on the cascading failure evolution in CPPS.

eess.SY↗

arXiv2022

Generating Connected, Simple, and Realistic Cyber Graphs for Smart Grids

Smart grids integrate communication systems with power networks to enable power grids operation and command through real-time data collection and control signals. Designing, analyzing, and simulating smart grid infrastructures as well as predicting the impact of power network failures strongly depend on the topologies of the underlying power network and communication system. Despite the substantial impact that the communication systems bring to smart grid operation, the topology of communication systems employed in smart grids was less studied. The power community lacks realistic generative communication system models that can be calibrated to match real-world data. To address this issue, this paper proposes a framework to generate the underlying topological graphs for the communication systems deployed in smart grids by mimicking the topology of real-world smart grids. In this regard, we have updated the Chung-Lu algorithm to guarantee the communication network connectivity and to match the degree distribution of a real-world smart grid rather than following an expected degree distribution. In addition, key characteristics of communication systems such as diameter, average shortest paths, clustering coefficients, assortativity, and spectral gap were taken into consideration to generate the most similar real-world communication network for smart grid studies. We believe that the proposed algorithm to generate realistic cyber graphs for smart grid studies will benefit the power community.

cs.SI↗

arXiv2021

Cyberattack Detection in Large-Scale Smart Grids using Chebyshev Graph Convolutional Networks

As a highly complex and integrated cyber-physical system, modern power grids are exposed to cyberattacks. False data injection attacks (FDIAs), specifically, represent a major class of cyber threats to smart grids by targeting the measurement data's integrity. Although various solutions have been proposed to detect those cyberattacks, the vast majority of the works have ignored the inherent graph structure of the power grid measurements and validated their detectors only for small test systems with less than a few hundred buses. To better exploit the spatial correlations of smart grid measurements, this paper proposes a deep learning model for cyberattack detection in large-scale AC power grids using Chebyshev Graph Convolutional Networks (CGCN). By reducing the complexity of spectral graph filters and making them localized, CGCN provides a fast and efficient convolution operation to model the graph structural smart grid data. We numerically verify that the proposed CGCN based detector surpasses the state-of-the-art model by 7.86 in detection rate and 9.67 in false alarm rate for a large-scale power grid with 2848 buses. It is notable that the proposed approach detects cyberattacks under 4 milliseconds for a 2848-bus system, which makes it a good candidate for real-time detection of cyberattacks in large systems.

cs.CR↗

arXiv2021

Hybrid RF/VLC Systems: A Comprehensive Survey on Network Topologies, Performance Analyses, Applications, and Future Directions

Wireless communications refer to data transmissions in unguided propagation media through the use of wireless carriers such as radio frequency (RF) and visible light (VL) waves. The rising demand for high data rates, especially, in indoor scenarios, overloads conventional RF technologies. Therefore, technologies such as millimeter waves (mmWave) and cognitive radios have been adopted as possible solutions to overcome the spectrum scarcity and capacity limitations of the conventional RF systems. In parallel, visible light communication (VLC) has been proposed as an alternative solution, where a light source is used for both illumination and data transmission. In comparison to RF links, VLC links present a very high bandwidth that allows much higher data rates. VLC exhibits also immunity to interference from electromagnetic sources, has unlicensed channels, is a very low power consumption system, and has no health hazard. VLC is appealing for a wide range of applications including reliable communications with low latency such as vehicle safety communication. Despite the major advantages of VLC technology and a variety of its applications, its use has been hampered by its cons such as its dependence on a line of sight connectivity. Recently, hybrid RF/VLC systems were proposed to take advantage of the high capacity of VLC links and better connectivity of RF links. Thus, hybrid RF/VLC systems are envisioned as a key enabler to improve the user rates and mobility on one hand and to optimize the capacity, interference and power consumption of the overall network on the other hand. This paper seeks to provide a detailed survey of hybrid RF/VLC systems. This paper represents an overview of the current developments in the hybrid RF/VLC systems, their benefits and limitations for both newcomers and expert researchers.

eess.SP↗

arXiv2021

Graph Neural Networks Based Detection of Stealth False Data Injection Attacks in Smart Grids

False data injection attacks (FDIAs) represent a major class of attacks that aim to break the integrity of measurements by injecting false data into the smart metering devices in power grids. To the best of authors' knowledge, no study has attempted to design a detector that automatically models the underlying graph topology and spatially correlated measurement data of the smart grids to better detect cyber attacks. The contributions of this paper to detect and mitigate FDIAs are twofold. First, we present a generic, localized, and stealth (unobservable) attack generation methodology and publicly accessible datasets for researchers to develop and test their algorithms. Second, we propose a Graph Neural Network (GNN) based, scalable and real-time detector of FDIAs that efficiently combines model-driven and data-driven approaches by incorporating the inherent physical connections of modern AC power grids and exploiting the spatial correlations of the measurement. It is experimentally verified by comparing the proposed GNN based detector with the currently available FDIA detectors in the literature that our algorithm outperforms the best available solutions by 3.14%, 4.25%, and 4.41% in F1 score for standard IEEE testbeds with 14, 118, and 300 buses, respectively.

eess.SP↗

arXiv2021

Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids using Graph Neural Networks

False data injection attacks (FDIA) are a main category of cyber-attacks threatening the security of power systems. Contrary to the detection of these attacks, less attention has been paid to identifying the attacked units of the grid. To this end, this work jointly studies detecting and localizing the stealth FDIA in power grids. Exploiting the inherent graph topology of power systems as well as the spatial correlations of measurement data, this paper proposes an approach based on the graph neural network (GNN) to identify the presence and location of the FDIA. The proposed approach leverages the auto-regressive moving average (ARMA) type graph filters (GFs) which can better adapt to sharp changes in the spectral domain due to their rational type filter composition compared to the polynomial type GFs such as Chebyshev. To the best of our knowledge, this is the first work based on GNN that automatically detects and localizes FDIA in power systems. Extensive simulations and visualizations show that the proposed approach outperforms the available methods in both detection and localization of FDIA for different IEEE test systems. Thus, the targeted areas can be identified and preventive actions can be taken before the attack impacts the grid.

cs.LG↗

arXiv2021

Utility of Traffic Information in Dynamic Routing: Is Sharing Information Always Useful?

Real-time traffic information can be utilized to enhance the efficiency of transportation networks by dynamically updating routing plans to mitigate traffic jams. However, an interesting question is whether the network coordinator should broadcast real-time traffic information to all network users or communicate it selectively to some of them. Which option enhances the network efficiency more? In this work, we demonstrate using simulation experiments that sharing real-time traffic information with all network users is sub-optimal, and it is actually better to share the information with a majority subset of the total population in order to improve the overall network performance. This result is valid under the assumption that each network user decides its route to destination locally.

cs.MA↗

arXiv2019

Blockchain-based Charging Coordination Mechanism for Smart Grid Energy Storage Units

Energy storage units (ESUs) enable several attractive features of modern smart grids such as enhanced grid resilience, effective demand response, and reduced bills. However, uncoordinated charging of ESUs stresses the power system and can lead to a blackout. On the other hand, existing charging coordination mechanisms suffer from several limitations. First, the need for a central charging coordinator (CC) presents a single point of failure that jeopardizes the effectiveness of the charging coordination. Second, a transparent charging coordination mechanism does not exist where users are not aware whether the CC is honest or not in coordination charging requests among them in a fair way. Third, existing mechanisms overlook the privacy concerns of the involved customers. To address these limitations, in this paper, we leverage the blockchain and smart contracts to build a decentralized charging coordination mechanism without the need for a centralized charging coordinator. First ESUs should use tokens for anonymously authenticate themselves to the blockchain. Then each ESU sends a charging request that contains its State-of-Charge (SoC), Time-to-complete-charge (TCC) and amount of required charging to the smart contract address on the blockchain. The smart contract will then run the charging coordination mechanism in a self-executed manner such that ESUs with the highest priorities are charged in the present time slot while charging requests of lower priority ESUs are deferred to future time slots. In this way, each ESU can make sure that charging schedules are computed correctly. Finally, we have implemented the proposed mechanism on the Ethereum test-bed blockchain, and our analysis shows that execution cost can be acceptable in terms of gas consumption while enabling decentralized charging coordination with increased transparency, reliability, and privacy preserving.

cs.CR↗

arXiv2019

In Vivo Communications: Steps Toward the Next Generation of Implantable Devices

In vivo wireless medical devices have the potential to play a vital role in future healthcare technologies by improving the quality of human life. In order to fully exploit the capabilities of such devices, it is necessary to characterize and model the in vivo wireless communication channel. Utilization of this model will have a significant role in improving the communication performance of embedded medical devices in terms of power, reliability and spectral efficiency. In this paper, the state of the art in this field is presented to provide a comprehensive understanding of current models. Such knowledge will be used to optimize the design and selection of various in vivo wireless communication methods, operational frequencies, and antenna design. Finally, open research areas are discussed for future studies.

eess.SP↗

arXiv2018

Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters

Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers' electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector's performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.

cs.LG↗

arXiv2017

From D2D to Ds2D: Prolonging the Battery Life of Mobile Devices via Ds2D Communications

Emerging device centric systems (DCS) such as device-to-device (D2D) communications are considered as a standard part of future mobile networks, where operators/consumers involve the devices in direct communication to improve the cellular system throughput, latency, fairness, and energy efficiency. However, battery life of mobile devices involved in such communications is crucial for 5G smartphone users to explore the emerging applications in DCS. It is anticipated that the owners of 5G-enabled smartphones use their devices more extensively to talk, text, email, and surf the Web more often than do customers with 4G smartphones or traditional handsets, which puts a significantly higher demand on the battery life. Smartphones are currently equipped with multiple radio interfaces that enable them to access different types of wireless networks including LTE-direct and Wi-Fi-direct, besides cellular networks. Such a capability is not well explored within the context of DCS. This article proposes a new scheme to support the emerging features in DCS where a D2D-enabled mobile device (sink device or a file/content requester) aggregates the radio resources of multiple mobile devices (source devices or file/content providers) via its multiple radio interfaces such that the scheme is referred to as devices-to-device (Ds2D) communications. Ds2D communication scheme ensures an optimal packet split among the source mobile devices to improve the file/content transfer latency (FTL), energy efficiency, and battery life. Simulation results demonstrate that the proposed optimal packet split scheme among multiple source devices participating in Ds2D communication scheme guarantees an improvement in mobile battery life over wide range of data rate levels in comparison with the random packet split strategy and traditional D2D communication paradigm between the sink and source mobile devices.

cs.NI↗