arXiv subjects

Payel Bhattacharjee

Publications and source records attributed to Payel Bhattacharjee.

7 recordsLinked to original sources

arXiv2026

STAMP: Selective Task-Aware Mechanism for Text Privacy

We present STAMP (Selective Task-Aware Mechanism for Text Privacy), a new framework for task-aware text privatization that achieves an improved privacy-utility trade-off. STAMP selectively allocates privacy budgets across tokens by jointly considering (i) each token's importance to the downstream task (as measured via a task- or query-specific representation), and (ii) its privacy sensitivity (e.g., names, dates, identifiers). This token-level partitioning enables fine-grained, group-wise control over the level of noise applied to different parts of the input, balancing privacy protection with task relevance. To privatize individual token embeddings, we introduce the polar mechanism, which perturbs only the direction of embeddings on the unit sphere while preserving their magnitude. Decoding is performed via cosine nearest-neighbor search, aligning the perturbation geometry with the decoding geometry. Unlike isotropic noise mechanisms, the polar mechanism maintains semantic neighborhoods in the embedding space and better preserves downstream utility. Experimental evaluations on SQuAD, Yelp, and AG News datasets demonstrate that STAMP, when combined with the normalized polar mechanism, consistently achieves superior privacy-utility trade-offs across varying per-token privacy budgets.

cs.LG↗

arXiv2026

MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling

Reward modeling is central to RLHF, RLAIF, and PPO-based alignment, but its reliability is often limited by scarce and heterogeneous human preference data. In this paper, we introduce MARS (Margin and Semantic-Aware Data Augmentation for Reward Modeling), an adaptive augmentation framework for controlled low-resource reward modeling. MARS allocates more augmentation to low-margin preference pairs and uses semantic-distance-based refinement to improve chosen-rejected contrast before generating synthetic preference samples. Across three preference datasets, two reward-model backbones, and downstream alignment evaluations, MARS improves average RewardBench performance and alignment win rates over uniform augmentation, WoN, and AdaBoost-style baselines. Ablations and independent-judge evaluations suggest that the gains are not solely explained by semantic refinement alone or GPT-4.1 judge coupling.

cs.LG↗

arXiv2025

Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding

Edge-cloud speculative decoding (SD) accelerates inference by having a cloud-based large language model (LLM) that verifies draft tokens generated by a resource-constrained small language model (SLM) at the edge. A central bottleneck is the limited bandwidth of the edge-cloud link, which necessitates efficient compression of draft token distributions. We first derive an information-theoretic bound that decomposes the token rejection rate into contributions from SLM-LLM distribution mismatch and from quantization distortion. Guided by this analysis, we propose the Sparse Quantize-and-Sample SD (SQS-SD) framework, which exploits distributional sparsity through structured sparsification and lattice-based quantization. Within this framework, K-SQS applies fixed top-K truncation, while C-SQS adaptively adjusts the retained token set via online conformal prediction to ensure bounded deviation from the dense distribution. Empirical results confirm that both approaches improve end-to-end latency and rejection rates in complimentary operating regimes.

cs.LG↗

arXiv2025

PROPS: Progressively Private Self-alignment of Large Language Models

Alignment is a key step in developing Large Language Models (LLMs) using human feedback to ensure adherence to human values and societal norms. Dependence on human feedback raises privacy concerns about how much a labeler's preferences may reveal about their personal values, beliefs, and personality traits. Existing approaches, such as Differentially Private SGD (DP-SGD), provide rigorous privacy guarantees by privatizing gradients during fine-tuning and alignment but can provide more privacy than necessary as human preferences are tied only to labels of (prompt, response) pairs and can degrade model utility. This work focuses on LLM alignment with preference-level privacy, which preserves the privacy of preference labels provided by humans. We propose PROPS (PROgressively Private Self-alignment), a multi-stage privacy preserving alignment framework where privately aligned models in previous stages can serve as labelers for supplementing training data in the subsequent stages of alignment. We present theoretical guarantees for PROPS as well as comprehensive validation using multiple models (Pythia and GPT) and datasets (AlpacaEval, Anthropic HH-RLHF, truthy-dpo-v0.1) to demonstrate the utility of PROPS over existing methods while still providing high privacy. For the same privacy budget, alignment via PROPS can achieve up to 3x higher win-rates compared to DP-SGD, and 2.5x higher win-rates compared to Randomized Response (RR) based alignment.

cs.LG↗

arXiv2025

Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data

Epidemic analyses increasingly rely on heterogeneous datasets, many of which are sensitive and require strong privacy protection. Although differential privacy (DP) has become a standard in machine learning and data sharing, its adoption in epidemiological modeling remains limited. In this work, we introduce DPEpiNN, a unified framework that integrates deep neural networks with a mechanistic SEIRM-based metapopulation model under formal DP guarantees. DPEpiNN supports multiple epidemic tasks (including multi-step forecasting, nowcasting, effective reproduction number $(R_t)$ estimation, and intervention analysis) within a single differentiable pipeline. The framework jointly learns epidemic parameters from heterogeneous public and sensitive datasets, while ensuring privacy via input perturbation mechanisms. We evaluate DPEpiNN using COVID-19 data from three regions. Results show that incorporating sensitive datasets substantially improves predictive performance even under strong privacy constraints. Compared with a deep learning baseline, DPEpiNN achieves higher accuracy in forecasting and nowcasting while producing reliable estimates of $R_t$. Furthermore, the learned epidemic transmission models remain inherently private due to the post-processing property of differential privacy, enabling downstream policy analyses such as simulation of social distancing interventions. Our work demonstrates that interpretability (through mechanistic modeling), predictive accuracy (through neural integration), and rigorous privacy guarantees can be jointly achieved in modern epidemic modeling.

cs.LG↗

arXiv2025

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification

Large Language Models (LLMs) are increasingly adopted across domains such as education, healthcare, and finance. In healthcare, LLMs support tasks including disease diagnosis, abnormality classification, and clinical decision-making. Among these, multi-abnormality classification of radiology reports is critical for clinical workflow automation and biomedical research. Leveraging strong natural language processing capabilities, LLMs enable efficient processing of unstructured medical text and reduce the administrative burden of manual report analysis. To improve performance, LLMs are often fine-tuned on private, institution-specific datasets such as radiology reports. However, this raises significant privacy concerns: LLMs may memorize training data and become vulnerable to data extraction attacks, while sharing fine-tuned models risks exposing sensitive patient information. Despite growing interest in LLMs for medical text classification, privacy-preserving fine-tuning for multi-abnormality classification remains underexplored. To address this gap, we propose a differentially private (DP) fine-tuning framework for multi-abnormality classification from free-text radiology reports. Our approach integrates differential privacy with Low-Rank Adaptation (LoRA) to efficiently fine-tune LLMs on sensitive clinical data while mitigating leakage risks. We further employ labels generated by a larger LLM to train smaller models, enabling efficient inference under strong privacy guarantees. Experiments on MIMIC-CXR and CT-RATE demonstrate the effectiveness of our DP-LoRA framework across varying privacy regimes. On MIMIC-CXR, our method achieves weighted F1-scores up to 0.89 under moderate privacy budgets, approaching non-private LoRA (0.90) and full fine-tuning (0.96), confirming that strong privacy can be achieved with only modest performance trade-offs.

cs.CR↗

arXiv2024

CURATE: Scaling-up Differentially Private Causal Graph Discovery

Causal Graph Discovery (CGD) is the process of estimating the underlying probabilistic graphical model that represents joint distribution of features of a dataset. CGD-algorithms are broadly classified into two categories: (i) Constraint-based algorithms (outcome depends on conditional independence (CI) tests), (ii) Score-based algorithms (outcome depends on optimized score-function). Since, sensitive features of observational data is prone to privacy-leakage, Differential Privacy (DP) has been adopted to ensure user privacy in CGD. Adding same amount of noise in this sequential-natured estimation process affects the predictive performance of the algorithms. As initial CI tests in constraint-based algorithms and later iterations of the optimization process of score-based algorithms are crucial, they need to be more accurate, less noisy. Based on this key observation, we present CURATE (CaUsal gRaph AdapTivE privacy), a DP-CGD framework with adaptive privacy budgeting. In contrast to existing DP-CGD algorithms with uniform privacy budgeting across all iterations, CURATE allows adaptive privacy budgeting by minimizing error probability (for constraint-based), maximizing iterations of the optimization problem (for score-based) while keeping the cumulative leakage bounded. To validate our framework, we present a comprehensive set of experiments on several datasets and show that CURATE achieves higher utility compared to existing DP-CGD algorithms with less privacy-leakage.

cs.CR↗