-
Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
38th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS 2024 D&B)
[Full Version]
[Conference Version]
[Code]
[Project Website]
[Slides]
[BibTex]
@inproceedings{
li2024infibench,
title={InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models},
author={Linyi Li and Shijie Geng and Zhenwen Li and Yibo He and Hao Yu and Ziyue Hua and Guanghan Ning and Siwei Wang and Tao Xie and Hongxia Yang},
booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2024},
}
キーワード：
LLM
benchmark
code
Summary
A comprehensive benchmark for code large language models (LLMs) evaluating model ability on answering freeform real-world questions in the code domain. From the evaluation of over 100 models, we summarize the empirical trends and scaling laws for existing open-source code LLMs.
-
Linyi Li
Certifiably Trustworthy Deep Learning Systems at Scale
Doctoral Thesis
[Full Version]
[Official Version]
[BibTex]
@phdthesis{li2023thesis,
title = {Certifiably Trustworthy Deep Learning Systems at Scale},
author = {Linyi Li},
year = 2023,
month = {Oct},
school = {University of Illinois Urbana-Champaign},
type = {PhD thesis}
}
キーワード：
certified ML
Summary
My PhD thesis. The thesis systematically summarizes the current research horizon of deep learning certified trustworthiness. Compared to the SoK paper, the thesis extends beyond just robustness and covers the technical details of representative methods.
-
Linyi Li, Tao Xie, Bo Li
SoK: Certified Robustness for Deep Neural Networks
44th IEEE Symposium on Security and Privacy (SP 2023)
[Full Version]
[Conference Version]
[Slides]
[Code]
[Leaderboard]
[BibTex]
@inproceedings{li2023sok,
author={Linyi Li and Tao Xie and Bo Li},
title = {SoK: Certified Robustness for Deep Neural Networks},
booktitle = {44th {IEEE} Symposium on Security and Privacy, {SP} 2023, San Francisco, CA, USA, 22-26 May 2023},
publisher = {{IEEE}},
year = {2023},
}
キーワード：
certified ML
Summary
A comprehensive systemization of knowledge on DNN certified robustness, including discussion on practical and theoretical implications, findings, main challenges, and future directions, accompanied with an open-source unified platform to evaluate 20+ representative approaches.
-
Linyi Li, Yuhao Zhang, Luyao Ren, Yingfei Xiong, Tao Xie
Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects
45th IEEE/ACM International Conference on Software Engineering (ICSE 2023)
[Full Version]
[Conference Version]
[Slides]
[Code]
[BibTex]
@inproceedings{li2023reliability,
author={Linyi Li and Yuhao Zhang and Luyao Ren and Yingfei Xiong and Tao Xie},
title = {Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects},
booktitle = {45th International Conference on Software Engineering, {ICSE} 2023, Melbourne, Australia, 14-20 May 2023},
publisher = {{IEEE/ACM}},
year = {2023},
}
キーワード：
certified ML
numerical reliability
Summary
An effective and efficient white-box framework for generic DNN architectures, named RANUM, for certifying numerical reliability (e.g., not output NaN or INF), generating failure-exhibiting system tests, and suggesting fixes, where RANUM is the first automated framework for the last two tasks.
-
Mintong Kang*, Linyi Li*, Maurice Weber, Yang Liu, Ce Zhang, Bo Li
Certifying Some Distributional Fairness with Subpopulation Decomposition
Advances in Neural Information Processing Systems (NeurIPS) 2022
[Full Version]
[Conference Version]
[Code]
[Poster]
[BibTex]
@inproceedings{kang2022certifying,
title = {Certifying Some Distributional Fairness with Subpopulation Decomposition},
author = {Mintong Kang and Linyi Li and Maurice Weber and Yang Liu and Ce Zhang and Bo Li},
booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
year = {2022}
}
キーワード：
certified ML
fairness
Summary
A practical and scalable certification approach to provide fairness bound for a given model when distribution shifts from training, based on subpopulation decomposition.
-
Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
Double Sampling Randomized Smoothing
39th International Conference on Machine Learning (ICML 2022)
[Conference Version]
[Full Version]
[Code]
[BibTex]
@inproceedings{
li2022double,
title={Double Sampling Randomized Smoothing},
author={Linyi Li and Jiawei Zhang and Tao Xie and Bo Li},
booktitle={39th International Conference on Machine Learning (ICML 2022)},
year={2022},
}
キーワード：
certified ML
Summary
A tighter certification approach for randomized smoothing, that for the first time circumvents the well-known curse of dimensionality under mild conditions by leveraging statistics from two strategically-chosen distributions.
-
Fan Wu*, Linyi Li*, Chejian Xu, Huan Zhang, Bhavya Kailkhura, Krishnaram Kenthapadi, Ding Zhao, Bo Li
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
10th International Conference on Learning Representations (ICLR 2022)
[Conference Version]
[Full Version]
[Leaderboard]
[Code]
[BibTex]
@inproceedings{
wu2022copa,
title={{COPA}: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks},
author={Fan Wu and Linyi Li and Chejian Xu and Huan Zhang and Bhavya Kailkhura and Krishnaram Kenthapadi and Ding Zhao and Bo Li},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=psh0oeMSBiF}
}
キーワード：
certified ML
deep reinforcement learning
Summary
The first approach for certifying deep RL robustness against offline training dataset perturbations, i.e., poisoning attacks, by aggregating over policies trained on partitioned datasets and policies for multiple time steps.
-
Zhuolin Yang*, Linyi Li*, Xiaojun Xu, Bhavya Kailkhura, Tao Xie, Bo Li
On the Certified Robustness for Ensemble Models and Beyond
10th International Conference on Learning Representations (ICLR 2022)
[Conference Version]
[Full Version]
[Code]
[BibTex]
@inproceedings{
yang2022on,
title={On the Certified Robustness for Ensemble Models and Beyond},
author={Zhuolin Yang and Linyi Li and Xiaojun Xu and Bhavya Kailkhura and Tao Xie and Bo Li},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=tUa4REjGjTf}
}
キーワード：
certified ML
Summary
Based on a curvature bound for randomized smoothing based classifiers, we prove that large confidence margin and gradient diversity are sufficient and necessary condition for certifiably robust ensembles. By regularizing these two factors, we acheive SOTA L2 certified robustness.
-
Zhuolin Yang*, Linyi Li*, Xiaojun Xu*, Shiliang Zuo, Qian Chen, Pan Zhou, Benjamin I. P. Rubinstein, Ce Zhang, Bo Li
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
Advances in Neural Information Processing Systems (NeurIPS) 2021
[Conference Version]
[Full Version]
[Code]
[BibTex]
@inproceedings{yangli2021trs,
title = {TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness},
author = {Zhuolin Yang and Linyi Li and Xiaojun Xu and Shiliang Zuo and Qian Chen and Pan Zhou and Benjamin I. P. Rubinstein and Ce Zhang and Bo Li},
booktitle = {Advances in Neural Information Processing Systems 34 (NeurIPS 2021)},
year = {2021}
}
キーワード：
robust ML
Summary
We prove the guaranteed correlation between model diversity and adversarial transferabiltiy given bounded model smoothness, which leads to a strong regularizer that achieves SOTA ensemble robustness against existing strong attacks.
-
Jiawei Zhang*, Linyi Li*, Huichen Li, Xiaolu Zhang, Shuang Yang, Bo Li
Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
International Conference on Machine Learning (ICML) 2021
[Conference Version]
[Full Version]
[Code]
[Slides]
[BibTex]
@inproceedings{zhangli2021progressive,
title = {Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation},
author = {Zhang, Jiawei and Li, Linyi and Li, Huichen and Zhang, Xiaolu and Yang, Shuang and Li, Bo},
booktitle = {Proceedings of the 38th International Conference on Machine Learning (ICML 2021)},
pages = {12479--12490},
year = {2021},
editor = {Meila, Marina and Zhang, Tong},
volume = {139},
series = {Proceedings of Machine Learning Research},
month = {18--24 Jul},
publisher = {PMLR},
}
キーワード：
attacks for ML
Summary
We systematically analyzed the gradient estimator that guides black-box attacks for DNNs, which reveals several key factors that can lead to more accurate gradient estimation with fewer queries. One way to realize these key factors is to conduct the attack with gradient estimation on a particularly scaled version of the image, which leads to the PSBA black-box attack with SOTA query effciency.
-
Linyi Li*, Maurice Weber*, Xiaojun Xu, Luka Rimanic, Bhavya Kailkhura, Tao Xie, Ce Zhang, Bo Li
TSS: Transformation-Specific Smoothing for Robustness Certification
ACM Conference on Computer and Communications Security (CCS) 2021
[Conference Version]
[Full Version]
[Code]
[Slides]
[BibTex]
@inproceedings{li2021tss,
title={TSS: Transformation-Specific Smoothing for Robustness Certification},
author={Linyi Li and Maurice Weber and Xiaojun Xu and Luka Rimanic and Bhavya Kailkhura and Tao Xie and Ce Zhang and Bo Li},
year={2021},
booktitle={ACM Conference on Computer and Communications Security (CCS 2021)}
}
キーワード：
certified ML
Summary
Natural transformations such as rotation and scaling are common in the physical world. We propose the first scalable certification approach against natural transformations based on randomzied smoothing, rigorous Lipschitz analysis, and stratified sampling. For the first time, we certify non-trivial robustness (>30% certified robust accuracy) on the large-scale ImageNet dataset.
-
Huichen Li*, Linyi Li*, Xiaojun Xu, Xiaolu Zhang, Shuang Yang, Bo Li
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
[Conference Version]
[Full Version]
[Code]
[BibTex]
@inproceedings{li2020nolinear,
title={Nonlinear Gradient Estimation for Query Efficient Blackbox Attack},
author={Huichen Li and Linyi Li and Xiaojun Xu and Xiaolu Zhang and Shuang Yang and Bo Li},
year={2021},
booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS 2021)},
series = {Proceedings of Machine Learning Research},
month = {13--15 Apr},
publisher = {PMLR},
}
キーワード：
attacks for ML
Summary
We analyze the outcome of using nonlinear projections for black-box gradient-estimation-based attacks, which shows that proper nonlinear projections can help to improve the attack efficiency.
-
Linyi Li, Zhenwen Li, Weijie Zhang, Jun Zhou, Pengcheng Wang, Jing Wu, Guanghua He, Xia Zeng, Yuetang Deng, Tao Xie
Clustering Test Steps in Natural Language toward Automating Test Automation
ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2020, Industry Track
[Paper]
[Video]
[BibTex]
@inproceedings{li2020clustep,
title = {Clustering Test Steps in Natural Language toward Automating Test Automation},
author = {Li, Linyi and Li, Zhenwen and Zhang, Weijie and Zhou, Jun and Wang, Pengcheng and Wu, Jing and He, Guanghua and Zeng, Xia and Deng, Yuetang and Xie, Tao},
booktitle = {Proceedings of the 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering {(ESEC/FSE 2020)}},
year = {2020},
doi = {10.1145/3368089.3417067},
url = {https://doi.org/10.1145/3368089.3417067}
}
キーワード：
ML for software testing
Summary
We provide an effective pipeline to cluster test steps in natural language and then synthesize executable test cases, deployed for WeChat testing.
-
Linyi Li*, Zexuan Zhong*, Bo Li, Tao Xie
Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space
International Joint Conference on Artificial Intelligence (IJCAI) 2019
[Paper]
[Code]
[BibTex]
@inproceedings{li2019robustra,
title = {Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space},
author = {Li, Linyi and Zhong, Zexuan and Li, Bo and Xie, Tao},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019)},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
pages = {4711--4717},
year = {2019},
month = {7},
doi = {10.24963/ijcai.2019/654},
url = {https://doi.org/10.24963/ijcai.2019/654}
}
キーワード：
certified ML
Summary
We propose a training method for achieving certified robustness by regularizing only within the reference adversarial space from a jointly trained model to alleviate the optimization hardness and achieve higher certified robustness.
