Personal information

Activities

Employment (1)

Pennsylvania State University: State College, US

2021-08 to present | Assistant Professor (College of Information Science and Technology)
Employment
Source: Self-asserted source
Jinghui Chen

Works (50 of 55)

Items per page:
Page 1 of 2

Backdoor Contrastive Learning via Bi-level Trigger Optimization

The Twelfth International Conference on Learning Representations
2024 | Conference paper
Contributors: Sun, Weiyu; Zhang, Xinyu; Lu, Hao; Chen, Yingcong; Wang, Ting; Chen, Jinghui; Lin, Lu
Source: Self-asserted source
Jinghui Chen

Challenges of COVID-19 Case Forecasting in the US, 2020--2021

PLoS computational biology
2024 | Journal article
Contributors: Lopez, Velma K; Cramer, Estee Y; Pagano, Robert; Drake, John M; O’Dea, Eamon B; Adee, Madeline; Ayer, Turgay; Chhatwal, Jagpreet; Dalgic, Ozden O; Ladd, Mary A et al.
Source: Self-asserted source
Jinghui Chen

Defending against alignment-breaking attacks via robustly aligned llm

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics
2024 | Conference paper
Contributors: Cao, Bochuan; Cao, Yuanpu; Lin, Lu; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

FADAS: Towards Federated Adaptive Asynchronous Optimization

Forty-first International Conference on Machine Learning
2024 | Conference paper
Contributors: Wang, Yujia; Wang, Shiqiang; Lu, Songtao; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

Graph Adversarial Diffusion Convolution

Forty-first International Conference on Machine Learning
2024 | Conference paper
Contributors: Liu, Songtao; Chen, Jinghui; Fu, Tianfan; Lin, Lu; Zitnik, Marinka; Wu, Dinghao
Source: Self-asserted source
Jinghui Chen

On the Difficulty of Defending Contrastive Learning against Backdoor Attacks

USENIX Security Symposium
2024 | Conference paper
Contributors: Li, Changjiang; Pang, Ren; Cao, Bochuan; Xi, Zhaohan; Chen, Jinghui; Ji, Shouling; Wang, Ting
Source: Self-asserted source
Jinghui Chen

On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics
2024 | Conference paper
Contributors: Zhang, Hangfan; Guo, Zhimeng; Zhu, Huaisheng; Cao, Bochuan; Lin, Lu; Jia, Jinyuan; Chen, Jinghui; Wu, Dinghao
Source: Self-asserted source
Jinghui Chen

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization

arXiv preprint arXiv:2406.00045
2024 | Journal article
Contributors: Cao, Yuanpu; Zhang, Tianrong; Cao, Bochuan; Yin, Ziyi; Lin, Lu; Ma, Fenglong; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection

arXiv preprint arXiv:2406.16288
2024 | Journal article
Contributors: Lee, Jooyoung; Agrawal, Toshini; Uchendu, Adaku; Le, Thai; Chen, Jinghui; Lee, Dongwon
Source: Self-asserted source
Jinghui Chen

PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning

Annual Conference of the North American Chapter of the Association for Computational Linguistics
2024 | Conference paper
Contributors: Zhang, Tianrong; Xi, Zhaohan; Wang, Ting; Mitra, Prasenjit; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

Stealthy and persistent unalignment on large language models via backdoor injections

Annual Conference of the North American Chapter of the Association for Computational Linguistics
2024 | Conference paper
Contributors: Cao, Yuanpu; Cao, Bochuan; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration

The Twelfth International Conference on Learning Representations (ICLR)
2024 | Conference paper
Contributors: Wang, Yujia; Cao, Yuanpu; Wu, Jingcheng; Chen, Ruoyu; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

Unveiling the Secrets without Data: Can Graph Neural Networks Be Exploited through Data-Free Model Extraction Attacks?

USENIX Security Symposium
2024 | Conference paper
Contributors: Zhuang, Yuanxin; Shi, Chuan; Zhang, Mengmei; Chen, Jinghui; Lyu, Lingjuan; Zhou, Pan; Sun, Lichao
Source: Self-asserted source
Jinghui Chen

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

Proceedings of the AAAI Conference on Artificial Intelligence
2024 | Conference paper
Contributors: Yin, Ziyi; Ye, Muchao; Zhang, Tianrong; Wang, Jiaqi; Liu, Han; Chen, Jinghui; Wang, Ting; Ma, Fenglong
Source: Self-asserted source
Jinghui Chen

WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response

arXiv preprint arXiv:2405.14023
2024 | Journal article
Contributors: Zhang, Tianrong; Cao, Bochuan; Cao, Yuanpu; Lin, Lu; Mitra, Prasenjit; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

XPrompt: Explaining Large Language Model's Generation via Joint Prompt Attribution

arXiv preprint arXiv:2405.20404
2024 | Journal article
Contributors: Chang, Yurui; Cao, Bochuan; Wang, Yujia; Chen, Jinghui; Lin, Lu
Source: Self-asserted source
Jinghui Chen

A3fl: Adversarially adaptive backdoor attacks to federated learning

Thirty-seventh Conference on Neural Information Processing Systems
2023 | Conference paper
Contributors: Zhang, Hangfan; Jia, Jinyuan; Chen, Jinghui; Lin, Lu; Wu, Dinghao
Source: Self-asserted source
Jinghui Chen

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

Thirty-seventh Conference on Neural Information Processing Systems
2023 | Conference paper
Contributors: Xi, Zhaohan; Du, Tianyu; Li, Changjiang; Pang, Ren; Ji, Shouling; Chen, Jinghui; Ma, Fenglong; Wang, Ting
Source: Self-asserted source
Jinghui Chen

Do Language Models Plagiarize?

Proceedings of the Web Conference (WWW)
2023 | Journal article
Contributors: Lee, Jooyound; Le, Thai; Chen, Jinghui; Lee, Dongwon
Source: Self-asserted source
Jinghui Chen

Federated Learning with Projected Trajectory Regularization

arXiv preprint arXiv:2312.14380
2023 | Journal article
Contributors: Chen, Tiejin; Cao, Yuanpu; Wang, Yujia; Hsieh, Cho-Jui; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

Graph Contrastive Backdoor Attacks

Proceedings of the International Conference on Machine Learning (ICML)
2023 | Journal article
Contributors: Hangfan, Zhang; Chen, Jinghui; Lin, Lu; Jia, Jinyuan; Wu, Dinghao
Source: Self-asserted source
Jinghui Chen

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

Thirty-seventh Conference on Neural Information Processing Systems
2023 | Conference paper
Contributors: Cao, Bochuan; Li, Changjiang; Wang, Ting; Jia, Jinyuan; Li, Bo; Chen, Jinghui
Source: Self-asserted source
Jinghui Chen

International Workshop on Federated Learning in the Age of Foundation Models

Annual Conference on Neural Information Processing Systems
2023 | Conference paper
Contributors: Chen, Jinghui; Fan, Lixin; Joshi, Gauri; Karimireddy, Sai Praneeth; Patterson, Stacy; Wang, Shiqiang; Yu, Han
Source: Self-asserted source
Jinghui Chen

PAT: Geometry-Aware Hard-Label Black-Box Adversarial Attacks on Text

Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
2023 | Journal article
Contributors: Ye, Muchao; Chen, Jinghui; Miao, Chenglin; Liu, Han; Wang, Ting; Ma, Fenglong
Source: Self-asserted source
Jinghui Chen

Rocoursenet: Robust training of a prediction aware recourse model

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
2023 | Conference paper
Contributors: Guo, Hangzhi; Jia, Feiran; Chen, Jinghui; Squicciarini, Anna; Yadav, Amulya
Source: Self-asserted source
Jinghui Chen

RoCourseNet: Robust Training of a Prediction Aware Recourse Model

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
2023 | Conference paper
Contributors: Guo, Hangzhi; Jia, Feiran; Chen, Jinghui; Squicciarini, Anna; Yadav, Amulya
Source: Self-asserted source
Jinghui Chen

Spectral Augmentation for Self-Supervised Learning on Graphs

Proceedings of the International Conference on Learning Representations (ICLR)
2023 | Journal article
Contributors: Lu Lin; Jinghui Chen; Hongning Wang
Source: Self-asserted source
Jinghui Chen

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

Thirty-seventh Conference on Neural Information Processing Systems
2023 | Conference paper
Contributors: Ye, Muchao; Yin, Ziyi; Zhang, Tianrong; Du, Tianyu; Chen, Jinghui; Wang, Ting; Ma, Fenglong
Source: Self-asserted source
Jinghui Chen

VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Thirty-seventh Conference on Neural Information Processing Systems
2023 | Conference paper
Contributors: Yin, Ziyi; Ye, Muchao; Zhang, Tianrong; Du, Tianyu; Zhu, Jinguo; Liu, Han; Chen, Jinghui; Wang, Ting; Ma, Fenglong
Source: Self-asserted source
Jinghui Chen

PAT: Geometry-Aware Hard-Label Black-Box Adversarial Attacks on Text

2023-08-06 | Conference paper
Contributors: Muchao Ye; Jinghui Chen; Chenglin Miao; Han Liu; Ting Wang; Fenglong Ma
Source: check_circle
Crossref

Do Language Models Plagiarize?

2023-04-30 | Conference paper
Contributors: Jooyoung Lee; Thai Le; Jinghui Chen; Dongwon Lee
Source: check_circle
Crossref

Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization

Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS)
2022 | Journal article
Source: Self-asserted source
Jinghui Chen

Communication-Efficient Adaptive Federated Learning

Proceedings of the International Conference on Machine Learning (ICML)
2022 | Journal article
Source: Self-asserted source
Jinghui Chen

Efficient robust training via backward smoothing

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
2022 | Journal article
Source: Self-asserted source
Jinghui Chen

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the US

Proceedings of the National Academy of Sciences
2022 | Journal article
Source: Self-asserted source
Jinghui Chen

LeapAttack: Hard-Label Adversarial Attack on Text via Gradient-Based Optimization

Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
2022 | Journal article
Contributors: Ye, Muchao; Chen, Jinghui; Miao, Chenglin; Wang, Ting; Ma, Fenglong
Source: Self-asserted source
Jinghui Chen

Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

Proceeding of the 10th International Conference on Learning Representations (ICLR)
2022 | Journal article
Source: Self-asserted source
Jinghui Chen

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

Advances in Neural Information Processing Systems (NeurIPS)
2022 | Journal article
Contributors: Shuwen Chai; Jinghui Chen
Source: Self-asserted source
Jinghui Chen

Do Wider Neural Networks Really Help Adversarial Robustness?

Proceedings of Advances in Neural Information Processing Systems (NeurIPS)
2021 | Journal article
Source: Self-asserted source
Jinghui Chen

A Frank-Wolfe framework for efficient and effective adversarial attacks

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

Closing the generalization gap of adaptive gradient methods in training deep neural networks

Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

COVID-19 reopening strategies at the county level in the face of uncertainty: Multiple Models for Outbreak Decision Support

medRxiv
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

Ensemble forecasts of coronavirus disease 2019 (COVID-19) in the US

MedRXiv
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

Epidemic model guided machine learning for COVID-19 forecasts in the United States

medRxiv
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

On the convergence of adaptive gradient methods for nonconvex optimization

arXiv preprint arXiv:1808.05671
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

Rays: A ray searching method for hard-label adversarial attack

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD)
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

Understanding the intrinsic robustness of image distributions using conditional generative models

Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)
2020 | Journal article
Source: Self-asserted source
Jinghui Chen

Covariate adjusted precision matrix estimation via nonconvex optimization

Proceedings of the International Conference on Machine Learning (ICML)
2018 | Journal article
Source: Self-asserted source
Jinghui Chen

Global convergence of Langevin dynamics based algorithms for nonconvex optimization

Proceedings of Advances in Neural Information Processing Systems (NeurIPS)
2018 | Journal article
Source: Self-asserted source
Jinghui Chen

Fast newton hard thresholding pursuit for sparsity constrained nonconvex optimization

Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)
2017 | Journal article
Source: Self-asserted source
Jinghui Chen
Items per page:
Page 1 of 2

Peer review (1 review for 1 publication/grant)

Review activity for Advanced theory and simulations. (1)