Linyi Li 李林翼 linyi2@illinois.edu PhD Candidate, CS@UIUC

About

I am Linyi Li, a Ph.D. candidate at Department of Computer Science, University of Illinois at Urbana-Champaign co-advised by Prof. Bo Li and Prof. Tao Xie.

I focus on making neural networks more secure and reliable guided by theory, verification, and static analysis. Currently, I am working on neural network verification and provably robust neural network training. I worked on the theory side of ensemble training, blackbox neural network attacks, applications of machine learning, and software testing. I have broad interests in theory, programming languages, machine learning, and software engineering.

I got my bachelor's degree from Department of Computer Science and Technology, Tsinghua University in 2018, where I did research on Web API Automated Testing, advised by Prof. Xiaoying Bai.

[Curriculum Vitae]

News

Papers

("*" denotes to equal contribution)

  1. 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
    Neural Information Processing Systems (NeurIPS) 2021
    [Paper]  
    @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 = {Neural Information Processing Systems (NeurIPS 2021)},
    year = {2021}
    }
  2. Zhuolin Yang*, Linyi Li*, Xiaojun Xu, Bhavya Kailkhura, Tao Xie, Bo Li
    On the Certified Robustness for Ensemble Models and Beyond
    arXiv: 2107.10873
    [Paper]  
    @article{yang2021certified,
    title={On the Certified Robustness for Ensemble Models and Beyond},
    author={Yang, Zhuolin and Li, Linyi and Xu, Xiaojun and Kailkhura, Bhavya and Xie, Tao and Li, Bo},
    journal={arXiv},
    year={2021},
    volume={abs/2107.10873}
    }
  3. Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li
    CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
    arXiv: 2106.09292
    [Paper]  
    @article{wu2021crop,
    title={CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing},
    author={Wu, Fan and Li, Linyi and Huang, Zijian and Vorobeychik, Yevgeniy and Zhao, Ding and Li, Bo},
    journal={arXiv},
    year={2021},
    volume={abs/2106.09292}
    }
  4. 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]  
    @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},
    }
  5. 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]  
    @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)} }
  6. 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
    [Paper]   [Code]  
    @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},
    }
  7. Zhonghan Niu, Zhaoxi Chen, Linyi Li, Yubin Yang, Bo Li, Jinfeng Yi
    On the Limitations of Denoising Strategies as Adversarial Defenses
    arXiv: 2012.09384
    [Paper]  
    @article{niu2020limitations,
    title={On the Limitations of Denoising Strategies as Adversarial Defenses},
    author={Zhonghan Niu and Zhaoxi Chen and Linyi Li and Yubin Yang and Bo Li and Jinfeng Yi},
    journal={arXiv},
    year={2020},
    volume={abs/2012.09384}
    }
  8. Linyi Li, Xiangyu Qi, Tao Xie, Bo Li
    SoK: Certified Robustness for Deep Neural Networks
    arXiv: 2009.04131
    [Paper]   [Code]  
    @article{li2020sok,
    title={SoK: Certified Robustness for Deep Neural Networks},
    author={Linyi Li and Xiangyu Qi and Tao Xie and Bo Li},
    year={2020},
    journal={arXiv},
    volume={abs/2009.04131}
    }
  9. 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]  
    @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}
    }
  10. 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]  
    @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}
    }
  11. Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson, Linyi Li
    Influence-Directed Explanations for Deep Convolutional Networks
    International Test Conference (ITC) 2018; arXiv: 1802.03788
    [Paper]  
    @inproceedings{leino2018influence,
    author={Leino, Klas and Sen, Shayak and Datta, Anupam and Fredrikson, Matt and Li, Linyi},
    booktitle={2018 IEEE International Test Conference (ITC)},
    title={Influence-Directed Explanations for Deep Convolutional Networks},
    year={2018},
    pages={1-8},
    }
  12. Junyi Wang, Xiaoying Bai, Linyi Li, Haoran Ma, Zhicheng Ji
    A Model-Based Framework For Cloud API Testing
    IEEE Computer Software and Applications Conference (COMSPAC) 2017
    [Paper]  
    @inproceedings{wang2017model,
    author={Wang, Junyi and Bai, Xiaoying and Li, Linyi and Ji, Zhicheng and Ma, Haoran},
    booktitle={2017 IEEE 41st Annual Computer Software and Applications Conference (COMPSAC)},
    title={A Model-Based Framework for Cloud API Testing},
    year={2017},
    volume={2},
    pages={60-65},
    doi={10.1109/COMPSAC.2017.24},
    ISSN={0730-3157},
    month={July},
    }
  13. Junyi Wang, Xiaoying Bai, Haoran Ma, Linyi Li, Zhicheng Ji
    Cloud API Testing
    IEEE International Conference on Software Verification and Validation Workshops (ICSTW) 2017
    [Paper]  
    @inproceedings{wang2017cloud,
    title={Cloud API testing},
    author={Wang, Junyi and Bai, Xiaoying and Ma, Haoran and Li, Linyi and Ji, Zhicheng},
    booktitle={2017 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)},
    pages={385--386},
    year={2017},
    organization={IEEE}
    }

Selected Projects

VeriGauge

SoK: Certified Robustness for Deep Neural Networks

As a young but impactful area, starting from 2017, there is a series of work in certified robustness for deep neural networks. We present a systematization of knowledge for recent progress in certified robustness for deep neural networks along with a thorough benchmark. Please check out our paper for the details!

Along with the paper, we released a toolkit for using about 20 popular neural network verification approaches on GitHub. We are also maintaining a repo for state-of-the-art certified robustness for deep neural networks. Welcome to use and contribute!

Paper Toolkit SOTA Board
Robustra

Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space

Robustra is an approach for training provable robust neural networks. The key innovation is that, instead of training over the whole perturbation space, we mutually train a pair of models on the adversarial space of the other model. By narrowing the space we improve the optimization effect and yield more robust neural networks. Particularly, on MNIST with epsilon = 0.1 l-infty ball, we reduce the provable error bound to 2.09%.

Paper Code
Lapis

Lapis: Scenario-Based Automatic Web API Testing

Lapis is an automatic scenario-based Web API tester. The tool reads OpenAPI specification script and scenario definition, then generates and executes test cases automatically. Several evaluation experiments reveal its high efficiency and strength in Web API testing. PyLapis, the latest tool written in Python, using specification language extended from OpenAPI 3.0, is about to release.

Neural Network Explanation

Application of Integrated Gradients on Diabetic Retinopathy Detection Network

The project applies integrated gradients, an influence analysis method, to a diabetic retinopathy detection convolutional neural network. The tool and framework supports multiple explaining configurations such as direct attributing and middle-layer filtered attributing. The attribution results can be used directly for lesion detection. The visualization result of each neuron's influence enabled further analysis of the neural network.

Poster
VEECloud

VEE@Cloud

A distributed web API testing system. Distributed cluster nodes send test request individually under center control. The distribution property makes it possible to generate heavy test load.

Paper
Ray Tracing

Ray Tracing Render Engine

  • A totally independent cross-platform graphics render engine.
  • Supported algorithms: Phong reflection model, ray tracing and photon mapping.
  • Supported light source: point light, and area light.
  • Supported model: DSL-specified model, and ".obj" format model.
  • Supported material: solid, and transparency with refraction.

Personal

Last Updated: Oct 6, 2021