Jun Sun

SAGA: Efficient and Large-Scale Detection of Near-Miss Clones with GPU Acceleration

2020

Clone detection on large code repository is necessary for many big code analysis tasks. The goal is to provide rich information on identical and similar code across projects. Detecting near-miss code clones on big code …

Solar3D: An Open-Source Tool for Estimating Solar Radiation in Urban Environments

2020 · ISPRS International Journal of Geo-Information

Solar3D is an open-source software application designed to interactively calculate solar irradiation on three-dimensional (3D) surfaces in a virtual environment constructed with combinations of 3D-city models, digital elevation models (DEMs), digital surface models (DSMs) and …

SOCRATES: Towards a Unified Platform for Neural Network Analysis

2020 · arXiv (Cornell University)

Studies show that neural networks, not unlike traditional programs, are subject to bugs, e.g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness. Given that neural networks are increasingly …

Plume: Fast Finality Blockchain without Single Failure Point

2021

Bitcoin’s slow finality is an important factor preventing it from being widely used in real life. And other public single-chain blockchains have the same problem. In this paper, we propose a practical new protocol called …

Verifying Neural Networks Against Backdoor Attacks

2022 · Lecture notes in computer science

Abstract Neural networks have achieved state-of-the-art performance in solving many problems, including many applications in safety/security-critical systems. Researchers also discovered multiple security issues associated with neural networks. One of them is backdoor attacks, i.e., a …

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

2024 · arXiv (Cornell University)

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts even when aligned …