Junjie Zhang

Mission-Aware Vulnerability Assessment for Cyber-Physical Systems

2015 · 2015 IEEE Trustcom/BigDataSE/ISPA

Designing secure cyber-physical systems (CPS) is fundamentally important and performing vulnerability assessment becomes indispensable. In this paper, we discuss our ongoing work on building an automated mission-aware vulnerability CPS assessment framework that can accomplish three …

To Balance or Not to Balance: An Embarrassingly Simple Approach for Learning with Long-Tailed Distributions.

2019 · arXiv (Cornell University)

Real-world visual data often exhibits a long-tailed distribution, where some ''head'' classes have a large number of samples, yet only a few samples are available for ''tail'' classes. Such imbalanced distribution causes a great challenge …

PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning

2020 · arXiv (Cornell University)

The predicament in semi-supervised few-shot learning (SSFSL) is to maximize the value of the extra unlabeled data to boost the few-shot learner. In this paper, we propose a Poisson Transfer Network (PTN) to mine the …

Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation

2024 · arXiv (Cornell University)

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective …

Optical Field-to-Field Translation Under Atmospheric Turbulence: A Conditional GAN Framework with Embedded Turbulence Parameters

2025 · Photonics

We propose a field mapping approach for the propagation of laser beams through atmospheric turbulence, leveraging a Generative Adversarial Network (GAN). The proposed GAN utilizes a U-Net architecture as its generator, with turbulence characteristic parameters …

Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

As an emerging distributed learning paradigm, Federated Learning (FL) facilitates collaborative training among multiple clients without sharing raw data. However, the classic FL still faces significant challenges due to feature/model heterogeneity and catastrophic forgetting, which …

A Survey of Large Language Models

2026 · Frontiers of Computer Science

Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities, …