arXiv subjects

Yash Gupta

Publications and source records attributed to Yash Gupta.

13 recordsLinked to original sources

arXiv2026

Active Control of Topological Exceptional Points in Non-Hermitian Metasurfaces

Active control and ultrafast switching of non-Hermitian photonic systems are essential for next-generation reconfigurable optical technologies. Here, we demonstrate dynamic temporal manipulation of EPs in the terahertz (THz) regime using optically excited germanium (Ge) as an active medium. By exploiting pump-probe delay as a continuous tuning parameter, we achieve sub-picosecond eigenmode switching (~0.5 ps) and realize a complete time-resolved EP encirclement within ~2 ps, enabling direct observation of topological phase accumulation. At EP, the metasurface exhibits highly asymmetric transmission for circularly polarized light, characteristic of chiral mode response. Furthermore, we observe ultrafast eigenmode switching and topological phase evolution within ~1 ps, achieving >99% cross-polarization modulation depth. The measured results show strong agreement with theoretical modeling, with a high Petermann factor of approximately 10^3, confirming the effectiveness of the design. Our work establishes pump-probe delay time as a dynamical control parameter for EP topology, introducing a new regime of ultrafast non-Hermitian photonics for high-speed switching, enhanced sensitivity, and tunable polarization control in the THz domain.

physics.optics↗

arXiv2025

Hardware-Efficient CNNs: Interleaved Approximate FP32 Multipliers for Kernel Computation

Single-precision floating point (FP32) data format, defined by the IEEE 754 standard, is widely employed in scientific computing, signal processing, and deep learning training, where precision is critical. However, FP32 multiplication is computationally expensive and requires complex hardware, especially for precisely handling mantissa multiplication. In practical applications like neural network inference, perfect accuracy is not always necessary, minor multiplication errors often have little impact on final accuracy. This enables trading precision for gains in area, power, and speed. This work focuses on CNN inference using approximate FP32 multipliers, where the mantissa multiplication is approximated by employing error-variant approximate compressors, that significantly reduce hardware cost. Furthermore, this work optimizes CNN performance by employing differently approximated FP32 multipliers and studying their impact when interleaved within the kernels across the convolutional layers. The placement and ordering of these approximate multipliers within each kernel are carefully optimized using the Non-dominated Sorting Genetic Algorithm-II, balancing the trade-off between accuracy and hardware efficiency.

cs.AR↗

arXiv2025

The Untapped Potential of Smart Charging: How EV Owners Can Save Money and Reduce Emissions Without Behavioral Change

The transportation sector is the single largest contributor to US emissions and the second largest globally. Electric vehicles (EVs) are expected to represent half of global car sales by 2035, emerging as a pivotal solution to reduce emissions and enhance grid flexibility. The electrification of buildings, manufacturing, and transportation is expected to grow electricity demand substantially over the next decade. Without effectively managed EV charging, EVs could strain energy grid infrastructure and increase electricity costs. Drawing on de-identified 2023 EV telematics data from Rivian Automotive, this study found that 72% of home charging commenced after the customer plugged in their vehicle regardless of utility time of use (TOU) tariffs or managed charging programs. In fewer than 26% of charging sessions in the sample, EV owners actively scheduled charging times to align or participate in utility tariffs or programs. With a majority of drivers concurrently plugged in during optimal charging periods yet not actively charging, the study identified an opportunity to reduce individual EV owner costs and carbon emissions through smarter charging habits without significant behavioral modifications or sacrifice in user preferences. By optimizing home charging schedules within existing plug-in and plug-out windows, the study suggests that EV owners can save an average of $140 annually and reduce the associated carbon emissions of charging their EV by as much as 28%.

eess.SY↗

arXiv2025

Federated Learning Framework via Distributed Mutual Learning

Federated Learning often relies on sharing full or partial model weights, which can burden network bandwidth and raise privacy risks. We present a loss-based alternative using distributed mutual learning. Instead of transmitting weights, clients periodically share their loss predictions on a public test set. Each client then refines its model by combining its local loss with the average Kullback-Leibler divergence over losses from other clients. This collaborative approach both reduces transmission overhead and preserves data privacy. Experiments on a face mask detection task demonstrate that our method outperforms weight-sharing baselines, achieving higher accuracy on unseen data while providing stronger generalization and privacy benefits.

cs.LG↗

arXiv2024

BiLSTM and Attention-Based Modulation Classification of Realistic Wireless Signals

This work proposes a novel and efficient quadstream BiLSTM-Attention network, abbreviated as QSLA network, for robust automatic modulation classification (AMC) of wireless signals. The proposed model exploits multiple representations of the wireless signal as inputs to the network and the feature extraction process combines convolutional and BiLSTM layers for processing the spatial and temporal features of the signal, respectively. An attention layer is used after the BiLSTM layer to emphasize the important temporal features. The experimental results on the recent and realistic RML22 dataset demonstrate the superior performance of the proposed model with an accuracy up to around 99%. The model is compared with other benchmark models in the literature in terms of classification accuracy, computational complexity, memory usage, and training time to show the effectiveness of our proposed approach.

cs.LG↗

arXiv2023

Responsible AI (RAI) Games and Ensembles

Several recent works have studied the societal effects of AI; these include issues such as fairness, robustness, and safety. In many of these objectives, a learner seeks to minimize its worst-case loss over a set of predefined distributions (known as uncertainty sets), with usual examples being perturbed versions of the empirical distribution. In other words, aforementioned problems can be written as min-max problems over these uncertainty sets. In this work, we provide a general framework for studying these problems, which we refer to as Responsible AI (RAI) games. We provide two classes of algorithms for solving these games: (a) game-play based algorithms, and (b) greedy stagewise estimation algorithms. The former class is motivated by online learning and game theory, whereas the latter class is motivated by the classical statistical literature on boosting, and regression. We empirically demonstrate the applicability and competitive performance of our techniques for solving several RAI problems, particularly around subpopulation shift.

cs.AI↗

arXiv2022

Identifying Security Risks in NFT Platforms

This paper examines the effects of inherent risks in the emerging technology of non-fungible tokens and proposes an actionable set of solutions for stakeholders in this ecosystem and observers. Web3 and NFTs are a fast-growing 300 billion dollar economy with some clear, highly publicized harms that came to light recently. We set out to explore the risks to understand their nature and scope, and if we could find ways to mitigate them. In due course of investigation, we recap the background of the evolution of the web from a client-server model to the rise of Web2.0 tech giants in the early 2000s. We contrast how the Web3 movement is trying to re-establish the independent style of the early web. In our research we discover a primary set of risks and harms relevant to the ecosystem, and classify them into a simple taxonomy while addressing their mitigations with solutions. We arrive at a set of solutions that are a combination of processes to be adopted, and technological changes or improvements to be incorporated into the ecosystem, to implement risk mitigations. By linking mitigations to individual risks, we are confident our recommendations will improve the security maturity of the growing Web3 ecosystem. We are not endorsing, or recommending specifically any particular product or service in our solution set. Nor are we compensated or influenced in any way by these companies to list these products in our research. The evaluations of products in our research have to simply be viewed as suggested improvements.

cs.CY↗

arXiv2021

Multi-Row, Multi-Span Distant Supervision For Table+Text Question

Question answering (QA) over tables and linked text, also called TextTableQA, has witnessed significant research in recent years, as tables are often found embedded in documents along with related text. HybridQA and OTT-QA are the two best-known TextTableQA datasets, with questions that are best answered by combining information from both table cells and linked text passages. A common challenge in both datasets, and TextTableQA in general, is that the training instances include just the question and answer, where the gold answer may match not only multiple table cells across table rows but also multiple text spans within the scope of a table row and its associated text. This leads to a noisy multi instance training regime. We present MITQA, a transformer-based TextTableQA system that is explicitly designed to cope with distant supervision along both these axes, through a multi-instance loss objective, together with careful curriculum design. Our experiments show that the proposed multi-instance distant supervision approach helps MITQA get state-of-the-art results beating the existing baselines for both HybridQA and OTT-QA, putting MITQA at the top of HybridQA leaderboard with best EM and F1 scores on a held out test set.

cs.CL↗

arXiv2021

Stateful Detection of Model Extraction Attacks

Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers. Recent work has shown that attackers can exploit these APIs to extract good approximations of such ML models, by querying them with samples of their choosing. We propose VarDetect, a stateful monitor that tracks the distribution of queries made by users of such a service, to detect model extraction attacks. Harnessing the latent distributions learned by a modified variational autoencoder, VarDetect robustly separates three types of attacker samples from benign samples, and successfully raises an alarm for each. Further, with VarDetect deployed as an automated defense mechanism, the extracted substitute models are found to exhibit poor performance and transferability, as intended. Finally, we demonstrate that even adaptive attackers with prior knowledge of the deployment of VarDetect, are detected by it.

cs.LG↗

arXiv2021

Creating and Implementing a Smart Speaker

We have seen significant advancements in Artificial Intelligence and Machine Learning in the 21st century. It has enabled a new technology where we can have a human-like conversation with the machines. The most significant use of this speech recognition and contextual understanding technology exists in the form of a Smart Speaker. We have a wide variety of Smart Speaker products available to us. This paper aims to decode its creation and explain the technology that makes these Speakers, "Smart."

cs.HC↗

arXiv2020

A Compressed Sensing Approach to Pooled RT-PCR Testing for COVID-19 Detection

We propose `Tapestry', a novel approach to pooled testing with application to COVID-19 testing with quantitative Reverse Transcription Polymerase Chain Reaction (RT-PCR) that can result in shorter testing time and conservation of reagents and testing kits. Tapestry combines ideas from compressed sensing and combinatorial group testing with a novel noise model for RT-PCR used for generation of synthetic data. Unlike Boolean group testing algorithms, the input is a quantitative readout from each test and the output is a list of viral loads for each sample relative to the pool with the highest viral load. While other pooling techniques require a second confirmatory assay, Tapestry obtains individual sample-level results in a single round of testing, at clinically acceptable false positive or false negative rates. We also propose designs for pooling matrices that facilitate good prediction of the infected samples while remaining practically viable. When testing $n$ samples out of which $k \ll n$ are infected, our method needs only $O(k \log n)$ tests when using random binary pooling matrices, with high probability. However, we also use deterministic binary pooling matrices based on combinatorial design ideas of Kirkman Triple Systems to balance between good reconstruction properties and matrix sparsity for ease of pooling. In practice, we have observed the need for fewer tests with such matrices than with random pooling matrices. This makes Tapestry capable of very large savings at low prevalence rates, while simultaneously remaining viable even at prevalence rates as high as 9.5\%. Empirically we find that single-round Tapestry pooling improves over two-round Dorfman pooling by almost a factor of 2 in the number of tests required. We validate Tapestry in simulations and wet lab experiments with oligomers in quantitative RT-PCR assays. Lastly, we describe use-case scenarios for deployment.

q-bio.QM↗

arXiv2019

A framework for the extraction of Deep Neural Networks by leveraging public data

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making black-box queries to it. However, none of these works is able to satisfy all the three essential criteria for practical model extraction: (1) the ability to work on deep learning models, (2) the non-requirement of domain knowledge and (3) the ability to work with a limited query budget. We design a model extraction framework that makes use of active learning and large public datasets to satisfy them. We demonstrate that it is possible to use this framework to steal deep classifiers trained on a variety of datasets from image and text domains. By querying a model via black-box access for its top prediction, our framework improves performance on an average over a uniform noise baseline by 4.70x for image tasks and 2.11x for text tasks respectively, while using only 30% (30,000 samples) of the public dataset at its disposal.

cs.LG↗

arXiv2015

Effective Handling of Urgent Jobs - Speed Up Scheduling for Computing Applications

A queue is required when a service provider is not able to handle jobs arriving over the time. In a highly flexible and dynamic environment, some jobs might demand for faster execution at run-time especially when the resources are limited and the jobs are competing for acquiring resources. A user might demand for speed up (reduced wait time) for some of the jobs present in the queue at run time. In such cases, it is required to accelerate (directly sending the job to the server) urgent jobs (requesting for speed up) ahead of other jobs present in the queue for an earlier completion of urgent jobs. Under the assumption of no additional resources, such acceleration of jobs would result in slowing down of other jobs present in the queue. In this paper, we formulate the problem of Speed Up Scheduling without acquiring any additional resources for the scheduling of on-line speed up requests posed by a user at run-time and present algorithms for the same. We apply the idea of Speed Up Scheduling to two different domains -Web Scheduling and CPU Scheduling. We demonstrate our results with a simulation based model using trace driven workload and synthetic datasets to show the usefulness of Speed Up scheduling. Speed Up provides a new way of addressing urgent jobs, provides a different evaluation criteria for comparing scheduling algorithms and has practical applications.

cs.PF↗