Jun Zhu

Embedding Secure Coding Instruction into the IDE

2015

Many of the security vulnerabilities common in today's software can be prevented with standard secure coding practices. Computer science students who will become the developers of that software need to learn about those practices so …

DP-space: Bayesian Nonparametric Subspace Clustering with Small-variance Asymptotics

2015

Subspace clustering separates data points ap-proximately lying on union of affine subspaces into several clusters. This paper presents a novel nonparametric Bayesian subspace cluster-ing model that infers both the number of sub-spaces and the dimension …

A Quantitative Evaluation Method of Satellite Network Control Protocol based on Multi-attribute Utility Theory

2016 · MATEC Web of Conferences

Satellite network control protocol plays an important part in satellite communication system. Different design schemes of protocol have very different protocol attribute values. It is difficult to select a proper protocol solution from many solution …

Generative Topic Embedding: a Continuous Representation of Documents

2016

Word embedding maps words into a lowdimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps documents onto a low-dimensional topic space, …

Forecast the Plausible Paths in Crowd Scenes

2017

Forecasting the future plausible paths of pedestrians in crowd scenes is of wide applications, but it still remains as a challenging task due to the complexities and uncertainties of crowd motions. To address these issues, …

ZhuSuan: A Library for Bayesian Deep Learning

2017 · arXiv (Cornell University)

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning …

Sparse Adversarial Perturbations for Videos

2018 · arXiv (Cornell University)

Although adversarial samples of deep neural networks (DNNs) have been intensively studied on static images, their extensions in videos are never explored. Compared with images, attacking a video needs to consider not only spatial cues …

A fuzzy clustering‐based denoising model for evaluating uncertainty in collaborative filtering recommender systems

2018 · Journal of the Association for Information Science and Technology

Recommender systems are effective in predicting the most suitable products for users, such as movies and books. To facilitate personalized recommendations, the quality of item ratings should be guaranteed. However, a few ratings might not …

Reward Shaping via Meta-Learning

2019 · arXiv (Cornell University)

Reward shaping is one of the most effective methods to tackle the crucial yet challenging problem of credit assignment in Reinforcement Learning (RL). However, designing shaping functions usually requires much expert knowledge and hand-engineering, and …

Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a discriminative nonparametric latent feature relational model (LFRM) for link prediction to automatically infer the dimensionality of latent features. Under the generic RegBayes (regularized Bayesian inference) framework, we handily incorporate the prediction loss …

Benchmarking Adversarial Robustness

2019 · arXiv (Cornell University)

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it …

ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning

2021

Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications. In this work, we consider semi-supervised continual learning (SSCL) that incrementally learns from partially labeled data. Observing …

Triple-Memory Networks: A Brain-Inspired Method for Continual Learning

2021 · IEEE Transactions on Neural Networks and Learning Systems

Continual acquisition of novel experience without interfering with previously learned knowledge, i.e., continual learning, is critical for artificial neural networks, while limited by catastrophic forgetting. A neural network adjusts its parameters when learning a new …

Memory Replay with Data Compression for Continual Learning

2022 · arXiv (Cornell University)

Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing work is mainly …

Accelerated Linearized Laplace Approximation for Bayesian Deep Learning

2022 · arXiv (Cornell University)

Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks. The generalized Gauss-Newton (GGN) approximation is typically introduced to improve their tractability. However, LA and …

USTC-Pickers: a Unified Set of seismic phase pickers Transfer learned for China

2023 · 地震学报：英文版

Current popular deep learning seismic phase pickers like PhaseNet and EQTransformer suffer from performance drop in China. To mitigate this problem, we build a unified set of customized seismic phase pickers for different levels of …

GAuV: A Graph-Based Automated Verification Framework for Perfect Semi-Honest Security of Multiparty Computation Protocols

2024

Proving the security of a Multiparty Computation (MPC) protocol is a difficult task. Under the current simulation-based definition of MPC, a security proof consists of a simulator, which is usually specific to the concrete protocol …

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning

2025

Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, particularly in terms of prediction accuracy. However, in real-world scenarios, especially in safety-critical applications, accuracy alone is insufficient; reliable uncertainty estimates are …