arXiv subjects

Divya Gupta

Publications and source records attributed to Divya Gupta.

16 recordsLinked to original sources

arXiv2026

Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures

The intersection of Artificial Intelligence (AI) and distributed systems has given rise to Federated Learning (FL), a paradigm that enables decentralized model training without compromising local data privacy. As organizational data silos grow, deploying complex machine learning models across highly distributed edge networks becomes a critical infrastructural challenge. Standard FL implementations suffer from severe vulnerabilities related to adversarial gradient updates and computational bottlenecks at the aggregation layer. This paper presents a novel, end-to-end distributed architecture that hardens FL pipelines using advanced cryptographic verification and optimized big data processing frameworks. We introduce a Zero-Knowledge Proof (ZKP) wrapper that cryptographically validates node computations before global aggregation, neutralizing model poisoning attacks without inspecting raw gradients. Additionally, we evaluate the system's performance using extreme gradient boosting models optimized for distributed edge execution. We formalize the mathematical transformation of the machine learning loss functions into Rank-1 Constraint Systems (R1CS) suitable for succinct verification. Extensive experimental results demonstrate that our hybrid architecture achieves a 94.2\% accuracy retention under adversarial conditions while maintaining scalable throughput across 1,000 parallel distributed nodes, effectively bridging the gap between rigorous cryptographic security and high-performance distributed AI.

cs.DC↗

arXiv2026

Polymerized spacetime dynamics with multifield source: Unraveling the pre-inflationary Universe

We study a multifield model in loop quantum cosmology for a maximally symmetric spacetime governed by the Einstein-Hilbert action minimally coupled to scalar fields. Using a Legendre transformation, we formulate the Hamiltonian dynamics in canonically equivalent geometrodynamical and Yang-Mills-type representations, incorporating nontrivial couplings through a geometric structure on the multifield configuration space. Implementing the $\bar{\mu}$-scheme polymerization, we obtain the loop-quantum-corrected Friedmann equations. By focusing on the two-field models as an example, we analyze the effective dynamics for specific potentials. The \textit{quantum bouncing, transition, and slow-roll inflationary} phases are investigated numerically, and viability of the models is assessed by evaluating the number of e-folds during the inflationary phase for certain given initial conditions. The global behavior of the background evolution is further examined through linear stability and dynamical-systems analyses.

gr-qc↗

arXiv2025

Enterprise AI Must Enforce Participant-Aware Access Control

Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data. While fine-tuning enhances performance by internalizing domain knowledge, it also introduces a critical security risk: leakage of confidential training data to unauthorized users. These risks are exacerbated when LLMs are combined with Retrieval-Augmented Generation (RAG) pipelines that dynamically fetch contextual documents at inference time. We demonstrate data exfiltration attacks on AI assistants where adversaries can exploit current fine-tuning and RAG architectures to leak sensitive information by leveraging the lack of access control enforcement. We show that existing defenses, including prompt sanitization, output filtering, system isolation, and training-level privacy mechanisms, are fundamentally probabilistic and fail to offer robust protection against such attacks. We take the position that only a deterministic and rigorous enforcement of fine-grained access control during both fine-tuning and RAG-based inference can reliably prevent the leakage of sensitive data to unauthorized recipients. We introduce a framework centered on the principle that any content used in training, retrieval, or generation by an LLM is explicitly authorized for \emph{all users involved in the interaction}. Our approach offers a simple yet powerful paradigm shift for building secure multi-user LLM systems that are grounded in classical access control but adapted to the unique challenges of modern AI workflows. Our solution has been deployed in Microsoft Copilot Tuning, a product offering that enables organizations to fine-tune models using their own enterprise-specific data.

cs.CR↗

arXiv2025

Personalized Artificial General Intelligence (AGI) via Neuroscience-Inspired Continuous Learning Systems

Artificial Intelligence has made remarkable advancements in recent years, primarily driven by increasingly large deep learning models. However, achieving true Artificial General Intelligence (AGI) demands fundamentally new architectures rather than merely scaling up existing models. Current approaches largely depend on expanding model parameters, which improves task-specific performance but falls short in enabling continuous, adaptable, and generalized learning. Achieving AGI capable of continuous learning and personalization on resource-constrained edge devices is an even bigger challenge. This paper reviews the state of continual learning and neuroscience-inspired AI, and proposes a novel architecture for Personalized AGI that integrates brain-like learning mechanisms for edge deployment. We review literature on continuous lifelong learning, catastrophic forgetting, and edge AI, and discuss key neuroscience principles of human learning, including Synaptic Pruning, Hebbian plasticity, Sparse Coding, and Dual Memory Systems, as inspirations for AI systems. Building on these insights, we outline an AI architecture that features complementary fast-and-slow learning modules, synaptic self-optimization, and memory-efficient model updates to support on-device lifelong adaptation. Conceptual diagrams of the proposed architecture and learning processes are provided. We address challenges such as catastrophic forgetting, memory efficiency, and system scalability, and present application scenarios for mobile AI assistants and embodied AI systems like humanoid robots. We conclude with key takeaways and future research directions toward truly continual, personalized AGI on the edge. While the architecture is theoretical, it synthesizes diverse findings and offers a roadmap for future implementation.

cs.AI↗

arXiv2024

TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs

Benchmarking is the de-facto standard for evaluating LLMs, due to its speed, replicability and low cost. However, recent work has pointed out that the majority of the open source benchmarks available today have been contaminated or leaked into LLMs, meaning that LLMs have access to test data during pretraining and/or fine-tuning. This raises serious concerns about the validity of benchmarking studies conducted so far and the future of evaluation using benchmarks. To solve this problem, we propose Private Benchmarking, a solution where test datasets are kept private and models are evaluated without revealing the test data to the model. We describe various scenarios (depending on the trust placed on model owners or dataset owners), and present solutions to avoid data contamination using private benchmarking. For scenarios where the model weights need to be kept private, we describe solutions from confidential computing and cryptography that can aid in private benchmarking. We build an end-to-end system, TRUCE, that enables such private benchmarking showing that the overheads introduced to protect models and benchmark are negligible (in the case of confidential computing) and tractable (when cryptographic security is required). Finally, we also discuss solutions to the problem of benchmark dataset auditing, to ensure that private benchmarks are of sufficiently high quality.

cs.CR↗

arXiv2024

TrustRate: A Decentralized Platform for Hijack-Resistant Anonymous Reviews

Reviews and ratings by users form a central component in several widely used products today (e.g., product reviews, ratings of online content, etc.), but today's platforms for managing such reviews are ad-hoc and vulnerable to various forms of tampering and hijack by fake reviews either by bots or motivated paid workers. We define a new metric called 'hijack-resistance' for such review platforms, and then present TrustRate, an end-to-end decentralized, hijack-resistant platform for authentic, anonymous, tamper-proof reviews. With a prototype implementation and evaluation at the scale of thousands of nodes, we demonstrate the efficacy and performance of our platform, towards a new paradigm for building products based on trusted reviews by end users without having to trust a single organization that manages the reviews.

cs.CR↗

arXiv2023

Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chains

This paper addresses privacy concerns in multi-agent reinforcement learning (MARL), specifically within the context of supply chains where individual strategic data must remain confidential. Organizations within the supply chain are modeled as agents, each seeking to optimize their own objectives while interacting with others. As each organization's strategy is contingent on neighboring strategies, maintaining privacy of state and action-related information is crucial. To tackle this challenge, we propose a game-theoretic, privacy-preserving mechanism, utilizing a secure multi-party computation (MPC) framework in MARL settings. Our major contribution is the successful implementation of a secure MPC framework, SecFloat on EzPC, to solve this problem. However, simply implementing policy gradient methods such as MADDPG operations using SecFloat, while conceptually feasible, would be programmatically intractable. To overcome this hurdle, we devise a novel approach that breaks down the forward and backward pass of the neural network into elementary operations compatible with SecFloat , creating efficient and secure versions of the MADDPG algorithm. Furthermore, we present a learning mechanism that carries out floating point operations in a privacy-preserving manner, an important feature for successful learning in MARL framework. Experiments reveal that there is on average 68.19% less supply chain wastage in 2 PC compared to no data share, while also giving on average 42.27% better average cumulative revenue for each player. This work paves the way for practical, privacy-preserving MARL, promising significant improvements in secure computation within supply chain contexts and broadly.

cs.AI↗

arXiv2022

Efficient ML Models for Practical Secure Inference

ML-as-a-service continues to grow, and so does the need for very strong privacy guarantees. Secure inference has emerged as a potential solution, wherein cryptographic primitives allow inference without revealing users' inputs to a model provider or model's weights to a user. For instance, the model provider could be a diagnostics company that has trained a state-of-the-art DenseNet-121 model for interpreting a chest X-ray and the user could be a patient at a hospital. While secure inference is in principle feasible for this setting, there are no existing techniques that make it practical at scale. The CrypTFlow2 framework provides a potential solution with its ability to automatically and correctly translate clear-text inference to secure inference for arbitrary models. However, the resultant secure inference from CrypTFlow2 is impractically expensive: Almost 3TB of communication is required to interpret a single X-ray on DenseNet-121. In this paper, we address this outstanding challenge of inefficiency of secure inference with three contributions. First, we show that the primary bottlenecks in secure inference are large linear layers which can be optimized with the choice of network backbone and the use of operators developed for efficient clear-text inference. This finding and emphasis deviates from many recent works which focus on optimizing non-linear activation layers when performing secure inference of smaller networks. Second, based on analysis of a bottle-necked convolution layer, we design a X-operator which is a more efficient drop-in replacement. Third, we show that the fast Winograd convolution algorithm further improves efficiency of secure inference. In combination, these three optimizations prove to be highly effective for the problem of X-ray interpretation trained on the CheXpert dataset.

cs.CR↗

arXiv2021

Multi-institution encrypted medical imaging AI validation without data sharing

Adoption of artificial intelligence medical imaging applications is often impeded by barriers between healthcare systems and algorithm developers given that access to both private patient data and commercial model IP is important to perform pre-deployment evaluation. This work investigates a framework for secure, privacy-preserving and AI-enabled medical imaging inference using CrypTFlow2, a state-of-the-art end-to-end compiler allowing cryptographically secure 2-party Computation (2PC) protocols between the machine learning model vendor and target patient data owner. A common DenseNet-121 chest x-ray diagnosis model was evaluated on multi-institutional chest radiographic imaging datasets both with and without CrypTFlow2 on two test sets spanning seven sites across the US and India, and comprising 1,149 chest x-ray images. We measure comparative AUROC performance between secure and insecure inference in multiple pathology classification tasks, and explore model output distributional shifts and resource constraints introduced by secure model inference. Secure inference with CrypTFlow2 demonstrated no significant difference in AUROC for all diagnoses, and model outputs from secure and insecure inference methods were distributionally equivalent. The use of CrypTFlow2 may allow off-the-shelf secure 2PC between healthcare systems and AI model vendors for medical imaging, without changes in performance, and can facilitate scalable pre-deployment infrastructure for real-world secure model evaluation without exposure to patient data or model IP.

cs.CR↗

arXiv2021

SIRNN: A Math Library for Secure RNN Inference

Complex machine learning (ML) inference algorithms like recurrent neural networks (RNNs) use standard functions from math libraries like exponentiation, sigmoid, tanh, and reciprocal of square root. Although prior work on secure 2-party inference provides specialized protocols for convolutional neural networks (CNNs), existing secure implementations of these math operators rely on generic 2-party computation (2PC) protocols that suffer from high communication. We provide new specialized 2PC protocols for math functions that crucially rely on lookup-tables and mixed-bitwidths to address this performance overhead; our protocols for math functions communicate up to 423x less data than prior work. Some of the mixed bitwidth operations used by our math implementations are (zero and signed) extensions, different forms of truncations, multiplication of operands of mixed-bitwidths, and digit decomposition (a generalization of bit decomposition to larger digits). For each of these primitive operations, we construct specialized 2PC protocols that are more communication efficient than generic 2PC, and can be of independent interest. Furthermore, our math implementations are numerically precise, which ensures that the secure implementations preserve model accuracy of cleartext. We build on top of our novel protocols to build SIRNN, a library for end-to-end secure 2-party DNN inference, that provides the first secure implementations of an RNN operating on time series sensor data, an RNN operating on speech data, and a state-of-the-art ML architecture that combines CNNs and RNNs for identifying all heads present in images. Our evaluation shows that SIRNN achieves up to three orders of magnitude of performance improvement when compared to inference of these models using an existing state-of-the-art 2PC framework.

cs.CR↗

arXiv2020

Secure Medical Image Analysis with CrypTFlow

We present CRYPTFLOW, a system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build two components. Our first component is an end-to-end compiler from TensorFlow to a variety of MPC protocols. The second component is an improved semi-honest 3-party protocol that provides significant speedups for inference. We empirically demonstrate the power of our system by showing the secure inference of real-world neural networks such as DENSENET121 for detection of lung diseases from chest X-ray images and 3D-UNet for segmentation in radiotherapy planning using CT images. In particular, this paper provides the first evaluation of secure segmentation of 3D images, a task that requires much more powerful models than classification and is the largest secure inference task run till date.

cs.CR↗

arXiv2020

Blockene: A High-throughput Blockchain Over Mobile Devices

We introduce Blockene, a blockchain that reduces resource usage at member nodes by orders of magnitude, requiring only a smartphone to participate in block validation and consensus. Despite being lightweight, Blockene provides a high throughput of transactions and scales to a large number of participants. Blockene consumes negligible battery and data in smartphones, enabling millions of users to participate in the blockchain without incentives, to secure transactions with their collective honesty. Blockene achieves these properties with a novel split-trust design based on delegating storage and gossip to untrusted nodes. We show, with a prototype implementation, that Blockene provides throughput of 1045 transactions/sec, and runs with very low resource usage on smartphones, pointing to a new paradigm for building secure, decentralized applications.

cs.DC↗

arXiv2020

CrypTFlow2: Practical 2-Party Secure Inference

We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both correct -- i.e., their outputs are bitwise equivalent to the cleartext execution -- and efficient -- they outperform the state-of-the-art protocols in both latency and scale. At the core of CrypTFlow2, we have new 2PC protocols for secure comparison and division, designed carefully to balance round and communication complexity for secure inference tasks. Using CrypTFlow2, we present the first secure inference over ImageNet-scale DNNs like ResNet50 and DenseNet121. These DNNs are at least an order of magnitude larger than those considered in the prior work of 2-party DNN inference. Even on the benchmarks considered by prior work, CrypTFlow2 requires an order of magnitude less communication and 20x-30x less time than the state-of-the-art.

cs.CR↗

arXiv2020

EinsteinPy: A Community Python Package for General Relativity

This paper presents EinsteinPy (version 0.3), a community-developed Python package for gravitational and relativistic astrophysics. Python is a free, easy to use a high-level programming language which has seen a huge expansion in the number of its users and developers in recent years. Specifically, a lot of recent studies show that the use of Python in Astrophysics and general physics has increased exponentially. We aim to provide a very high level of abstraction, an easy to use interface and pleasing user experience. EinsteinPy is developed keeping in mind the state of a theoretical gravitational physicist with little or no background in computer programming and trying to work in the field of numerical relativity or trying to use simulations in their research. Currently, EinsteinPy supports simulation of time-like and null geodesics and calculates trajectories in different background geometries some of which are Schwarzschild, Kerr, and KerrNewmann along with coordinate inter-conversion pipeline. It has a partially developed pipeline for plotting and visualization with dependencies on libraries like Plotly, matplotlib, etc. One of the unique features of EinsteinPy is a sufficiently developed symbolic tensor manipulation utilities which are a great tool in itself for teaching yourself tensor algebra which for many beginner students can be overwhelmingly tricky. EinsteinPy also provides few utility functions for hypersurface embedding of Schwarzschild spacetime which further will be extended to model gravitational lensing simulation.

gr-qc↗

arXiv2019

CrypTFlow: Secure TensorFlow Inference

We present CrypTFlow, a first of its kind system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build three components. Our first component, Athos, is an end-to-end compiler from TensorFlow to a variety of semi-honest MPC protocols. The second component, Porthos, is an improved semi-honest 3-party protocol that provides significant speedups for TensorFlow like applications. Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity guarantees to convert any semi-honest MPC protocol into an MPC protocol that provides malicious security. The malicious security of the protocols output by Aramis relies on integrity of the hardware and semi-honest security of MPC. Moreover, our system matches the inference accuracy of plaintext TensorFlow. We experimentally demonstrate the power of our system by showing the secure inference of real-world neural networks such as ResNet50 and DenseNet121 over the ImageNet dataset with running times of about 30 seconds for semi-honest security and under two minutes for malicious security. Prior work in the area of secure inference has been limited to semi-honest security of small networks over tiny datasets such as MNIST or CIFAR. Even on MNIST/CIFAR, CrypTFlow outperforms prior work.

cs.CR↗

arXiv2012

On Constant-Round Concurrent Zero-Knowledge from a Knowledge Assumption

In this work, we consider the long-standing open question of constructing constant-round concurrent zero-knowledge protocols in the plain model. Resolving this question is known to require non-black-box techniques. We consider non-black-box techniques for zero-knowledge based on knowledge assumptions, a line of thinking initiated by the work of Hada and Tanaka (CRYPTO 1998). Prior to our work, it was not known whether knowledge assumptions could be used for achieving security in the concurrent setting, due to a number of significant limitations that we discuss here. Nevertheless, we obtain the following results: 1. We obtain the first constant round concurrent zero-knowledge argument for \textbf{NP} in the plain model based on a new variant of knowledge of exponent assumption. Furthermore, our construction avoids the inefficiency inherent in previous non-black-box techniques such that those of Barak (FOCS 2001); we obtain our result through an efficient protocol compiler. 2. Unlike Hada and Tanaka, we do not require a knowledge assumption to argue the soundness of our protocol. Instead, we use a discrete log like assumption, which we call Diffie-Hellman Logarithm Assumption, to prove the soundness of our protocol. 3. We give evidence that our new variant of knowledge of exponent assumption is in fact plausible. In particular, we show that our assumption holds in the generic group model. 4. Knowledge assumptions are especially delicate assumptions whose plausibility may be hard to gauge. We give a novel framework to express knowledge assumptions in a more flexible way, which may allow for formulation of plausible assumptions and exploration of their impact and application in cryptography.

cs.CR↗