activity
20192025
most citedDecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

62 citations · 71 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025★ 1 cited

Understanding Silent Data Corruption in LLM Training

Jeffrey Ma, Hengzhi Pei, Leonard Lausen +1

As the scale of training large language models (LLMs) increases, one emergent failure is silent data corruption (SDC), where hardware produces incorrect computations without explic…

cs.LG2023★ 1 cited

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

Hengzhi Pei, Jinyuan Jia, Wenbo Guo +2

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defense…

cs.LG2022★ 1 cited

Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One

Yezhen Wang, Tong Che, Bo Li +4

Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the in…

cs.LG2021

Towards Generating Real-World Time Series Data

Hengzhi Pei, Kan Ren, Yuqing Yang +3

Time series data generation has drawn increasing attention in recent years. Several generative adversarial network (GAN) based methods have been proposed to tackle the problem usua…

cs.LG2020

Improving Certified Robustness via Statistical Learning with Logical Reasoning

Zhuolin Yang, Zhikuan Zhao, Boxin Wang +8

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification m…

cs.LG2019

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

Yuheng Zhang, Ruoxi Jia, Hengzhi Pei +3

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have r…