Institution profile

University of Pittsburgh

Academic institutionnorthamerica · us
Official website
Research library549linked papers
Opportunities0open roles
Selected work

Representative Papers

Seeding with Differentially Private Network Information

May 26, 2023arXiv.org

In public health applications such as HIV prevention, complete behavioral contact networks are often unavailable; only privacy-sensitive, sequential contact samples can be obtained. Method: This paper introduces the first differentially private influence maximization seeding algorithm, supporting both centralized and local privacy models. It integrates randomized data collection, cascade-based influence estimation from sampled cascades, and rigorous theoretical analysis of estimation error bounds—ensuring performance guarantees under limited samples. Contribution/Results: Experiments show that under centralized differential privacy, algorithmic performance degrades gracefully as the privacy budget decreases; under local differential privacy, a larger budget is required to maintain effectiveness—consistent with theoretical predictions. This work provides the first solution for identifying high-impact individuals in privacy-constrained public health interventions that simultaneously offers provable theoretical guarantees and empirical efficacy.

4 citationsRead paper

TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning

Sep 01, 2024IEEE Transactions on Dependable and Secure Computing

Malicious aggregators in multi-party federated learning pose severe gradient leakage and privacy risks. Method: This paper introduces Threshold Fully Homomorphic Encryption (TFHE) into secure aggregation for the first time, proposing a decentralized privacy-preserving training framework tolerant to a bounded number of malicious aggregators. It eliminates reliance on trusted third parties by integrating secure multi-party computation with formal verification, effectively countering novel disaggregation attacks. Contribution/Results: We provide rigorous theoretical proofs establishing strict differential privacy and collusion resistance. Empirical evaluation demonstrates that the framework maintains state-of-the-art model accuracy while reducing communication overhead by 29–45%, and delivers end-to-end privacy guarantees under diverse strong adversarial models, including active and adaptive adversaries.

3 citationsRead paper

Trust The Typical

Feb 04, 2026

This work addresses the limitations of existing safety mechanisms in large language models, which rely on known threat detection and suffer from high false-positive rates and vulnerability to attacks. The authors propose modeling safety alignment as an out-of-distribution detection problem in semantic space, learning the typical distribution of benign prompts without requiring harmful examples. This approach enables generalizable, cross-domain, and multilingual protection. By integrating semantic space modeling, GPU-optimized inference, and real-time guardrailing within the vLLM framework, the method achieves state-of-the-art performance across 18 safety benchmarks, reduces false positives by up to 40×, supports over 14 languages, and incurs less than 6% inference overhead.

1 citationsRead paper

Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning

Jan 28, 2026

This work addresses the limitations of existing medical reasoning verification methods, which rely on single-step retrieval and provide only scalar rewards, thereby lacking interpretability and dynamic knowledge acquisition. The authors propose a tool-augmented reinforcement learning agent framework that iteratively queries external medical corpora during verification and integrates trajectory-supervised iterative reinforcement learning with an adaptive curriculum mechanism. This approach enables dynamic evidence retrieval for the first time, substantially improving both verification efficiency and reliability. Evaluated on four medical reasoning benchmarks, the method significantly outperforms current state-of-the-art approaches, achieving a 23.5% absolute accuracy gain on MedQA and a 32.0% improvement on MedXpertQA, while reducing the required sampling budget by a factor of eight.

1 citationsRead paper

Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators

Jan 20, 2026

This work addresses the lack of a unified understanding of the design principles, applicability, and performance differences between Physics-Informed Neural Networks (PINNs) and Neural Operators (NOs), which hinders the development of reliable data-driven PDE solvers. It proposes the first unified analytical framework that systematically characterizes the design space of both approaches along three dimensions: learning objectives, mechanisms for embedding physical structure, and strategies for computational load distribution. By elucidating the intrinsic connections and fundamental distinctions between these methods, the study not only clarifies the positioning and performance origins of existing techniques but also provides theoretical guidance and novel pathways for designing efficient and robust PDE solvers that effectively integrate physical priors with data-driven learning.

1 citationsRead paper
Recent publications

Latest Papers