李林翼

西蒙菲沙大学计算机系助理教授。
[firstnamelowercase]_[lastnamelowercase]@sfu.ca
[个人简历(英文版)]

我是李林翼,西蒙菲莎大学计算机学院助理教授。

我的研究方向为机器学习、计算机安全、和软件工程。 具体地,我专注于:(1)构建可信深度学习系统,以实现针对噪声的可验证鲁棒性[IJCAI 2019] [ICLR 2022a] [ICML 2022a] [SP 2023],针对语义性变换的可验证鲁棒性[CCS 2021] [ICML 2022b],针对训练集扰动的可验证鲁棒性[ICLR 2022b],针对分布偏移的可验证鲁棒性[ICML 2022c],可验证公平性[NeurIPS 2022],可验证数值可靠性[ICSE 2023]等等。(2)以对齐和系统性评估为中心的大模型研究。 我亦进行过集成模型的鲁棒性研究[NeurIPS 2021],深度学习模型的黑盒攻击研究[ICML 2021] [AISTATS 2021],以及机器学习在软件测试中的应用研究[FSE 2020 Industry]。 我有幸获得Rising Stars in Data ScienceAdvML Rising Star Award,和Wing Kai Cheng奖学金,并有幸入围2022 Qualcomm Innovation Fellowship2022 Two Sigma PhD Fellowship

我有幸在李博教授与谢涛教授指导下于2023年在伊利诺伊大学厄巴纳分校计算机系获得博士学位。 我2018年本科毕业于清华大学计算机科学与技术系。在白晓颖教授的指导下,我进行了Web API自动化测试方向的研究。

对可信机器学习/大模型的研究感兴趣?招生与合作信息参见英文版主页。

科研成果

目前,我的研究主要针对
  1. 为给定的深度神经网络模型提供各种可信属性(鲁棒性、公平性、可靠性等)的严格保证;
  2. 通过模型设计、数据集构建、模型训练、后处理等提高这种机器学习的可信保证。
点击以浏览细节。
(*表示共同第一作者)

  • Linyi Li, Tao Xie, Bo Li
    SoK: Certified Robustness for Deep Neural Networks
    44th IEEE Symposium on Security and Privacy (SP 2023)
    [完整版论文]   [会议版论文]   [幻灯片]   [代码]   [SOTA排行榜]  
    @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},
    }

    关键词: 可验证机器学习

    总结 对 DNN 可验证稳健性研究的全面系统总结,包括实践和理论上的意义、发现、主要挑战和未来方向的讨论,以及一个开源统一工具箱来评估 20 多种代表性方法。

  • 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)
    [完整版论文]   [会议版论文]   [幻灯片]   [代码]  
    @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},
    }

    关键词: 可验证机器学习 数值可靠性

    总结 提出了RANUM:一种高效的白盒框架,适用于一般的人工神经网络模型,用于验证数值可靠性(例如,不输出NAN或INF)、面向缺陷触发的系统测试生成和修复生成。其中,RANUM是后两种任务的首个自动化框架。

  • 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
    [完整版论文]   [会议版论文]   [代码]   [海报]  
    @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}
    }

    关键词: 可验证机器学习 公平性

    总结 一种新的实用且可扩展的验证算法,当分布从训练偏移时,为给定模型提供公平性保证,基于统计亚群分解。

  • Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
    Double Sampling Randomized Smoothing
    39th International Conference on Machine Learning (ICML 2022)
    [会议版论文]   [完整版论文]   [代码]  
    @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},
    }

    关键词: 可验证机器学习

    总结 对随机平滑化方法的一种更紧的验证算法,其首次利用来自两种不同分布的统计数据,来实现更紧的稳健性界,并在宽松条件下首次突破众所周知的维数陷阱。

  • Wenda Chu, Linyi Li, Bo Li
    TPC: Transformation-Specific Smoothing for Point Cloud Models
    39th International Conference on Machine Learning (ICML 2022)
    [完整版论文]   [代码]  
    @inproceedings{
    chu2022tpc,
    title={TPC: Transformation-Specific Smoothing for Point Cloud Models},
    author={Wenda Chu and Linyi Li and Bo Li},
    booktitle={39th International Conference on Machine Learning (ICML 2022)},
    year={2022},
    }

    关键词: 可验证机器学习

    总结 通过扩展对图像分类模型的稳健性验证算法,我们为点云模型提供了最先进的关于几何变换意义下的稳健性验证算法,其核心思想基于对点云几何变换的解析性分析。

  • Maurice Weber, Linyi Li, Boxin Wang, Zhikuan Zhao, Bo Li, Ce Zhang
    Certifying Out-of-Domain Generalization for Blackbox Functions
    39th International Conference on Machine Learning (ICML 2022)
    [会议版论文]   [完整版论文]   [代码]  
    @inproceedings{
    weber2022certifying,
    title={Certifying Out-of-Domain Generalization for Blackbox Functions},
    author={Maurice Weber and Linyi Li and Boxin Wang and Zhikuan Zhao and Bo Li and Ce Zhang},
    booktitle={39th International Conference on Machine Learning (ICML 2022)},
    year={2022},
    }

    关键词: 可验证机器学习

    总结 一种针对分布偏移的模型泛化的高效验证算法,它不需要对模型的架构进行假设,只要分布偏移受 Hellinger 距离(一种f散度)的限制。核心方法基于 Gramian 矩阵的半正定性质。

  • 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)
    [会议版论文]   [完整版论文]   [SOTA排行榜]   [代码]  
    @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}
    }

    关键词: 可验证机器学习 深度强化学习

    总结 通过聚合在分区数据集上训练的策略和多重步骤下的策略,实现可验证的深度强化学习对离线训练数据集扰动(即荼毒攻击)的稳健性。

  • 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)
    [会议版论文]   [完整版论文]   [代码]  
    @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}
    }

    关键词: 可验证机器学习

    总结 基于随机平滑分类器的曲率界,我们证明了大的分类概率差和梯度多样性对于可验证的稳健集成模型是充分必要的条件。通过约束这两个因素,我们实现了目前为止最佳的 L2 范数扰动下的稳健性。

  • Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li
    CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
    10th International Conference on Learning Representations (ICLR 2022)
    [会议版论文]   [完整版论文]   [SOTA排行榜]   [代码]  
    @inproceedings{
    wu2022crop,
    title={{CROP}: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing},
    author={Fan Wu and Linyi Li and Zijian Huang and Yevgeniy Vorobeychik and Ding Zhao and Bo Li},
    booktitle={International Conference on Learning Representations},
    year={2022},
    url={https://openreview.net/forum?id=HOjLHrlZhmx}
    }

    关键词: 可验证机器学习 深度强化学习

    总结 通过将随机平滑化方法与一组基于轨迹的搜索算法相结合,我们提出了第一个用于验证深度强化学习对状态扰动的稳健性的高效算法。

  • 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
    [会议版论文]   [完整版论文]   [代码]  
    @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}
    }

    关键词: 鲁棒机器学习

    总结 我们证明了给定有界模型平滑度下,模型的多样性和对抗样本可迁移性之间的相关性,基于此,我们提出了强大的正则化器,该正则化器对集成模型实现了针对现有强攻击的最佳稳健性。

  • 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
    [会议版论文]   [完整版论文]   [代码]   [幻灯片]  
    @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)}
    }

    关键词: 可验证机器学习

    总结 旋转和缩放等变换在自然世界中很常见。 我们提出了第一个基于随机平滑、严格的 Lipschitz 分析和分层抽样的针对自然变换的高效稳健性验证方法。 我们首次在大规模 ImageNet 数据集上实现了较高的可验证稳健性(> 30% 的可验证稳健分类准确率)。

  • 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
    [论文]   [代码]  
    @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}
    }

    关键词: 可验证机器学习

    总结 我们提出了一种通过仅在联合训练模型的参考对抗空间内进行正则化来实现可验证稳健性的训练方法,以减轻优化难度并获得更高的可验证稳健性。

(*表示共同第一作者)

  1. Linyi Li, Tao Xie, Bo Li
    SoK: Certified Robustness for Deep Neural Networks
    44th IEEE Symposium on Security and Privacy (SP 2023)
    [完整版论文]   [会议版论文]   [幻灯片]   [代码]   [SOTA排行榜]  
    @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},
    }

    关键词: 可验证机器学习

    总结 对 DNN 可验证稳健性研究的全面系统总结,包括实践和理论上的意义、发现、主要挑战和未来方向的讨论,以及一个开源统一工具箱来评估 20 多种代表性方法。

  2. 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)
    [完整版论文]   [会议版论文]   [幻灯片]   [代码]  
    @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},
    }

    关键词: 可验证机器学习 数值可靠性

    总结 提出了RANUM:一种高效的白盒框架,适用于一般的人工神经网络模型,用于验证数值可靠性(例如,不输出NAN或INF)、面向缺陷触发的系统测试生成和修复生成。其中,RANUM是后两种任务的首个自动化框架。

  3. 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
    [完整版论文]   [会议版论文]   [代码]   [海报]  
    @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}
    }

    关键词: 可验证机器学习 公平性

    总结 一种新的实用且可扩展的验证算法,当分布从训练偏移时,为给定模型提供公平性保证,基于统计亚群分解。

  4. Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
    Double Sampling Randomized Smoothing
    39th International Conference on Machine Learning (ICML 2022)
    [会议版论文]   [完整版论文]   [代码]  
    @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},
    }

    关键词: 可验证机器学习

    总结 对随机平滑化方法的一种更紧的验证算法,其首次利用来自两种不同分布的统计数据,来实现更紧的稳健性界,并在宽松条件下首次突破众所周知的维数陷阱。

  5. 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)
    [会议版论文]   [完整版论文]   [SOTA排行榜]   [代码]  
    @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}
    }

    关键词: 可验证机器学习 深度强化学习

    总结 通过聚合在分区数据集上训练的策略和多重步骤下的策略,实现可验证的深度强化学习对离线训练数据集扰动(即荼毒攻击)的稳健性。

  6. 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)
    [会议版论文]   [完整版论文]   [代码]  
    @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}
    }

    关键词: 可验证机器学习

    总结 基于随机平滑分类器的曲率界,我们证明了大的分类概率差和梯度多样性对于可验证的稳健集成模型是充分必要的条件。通过约束这两个因素,我们实现了目前为止最佳的 L2 范数扰动下的稳健性。

  7. 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
    [会议版论文]   [完整版论文]   [代码]  
    @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}
    }

    关键词: 鲁棒机器学习

    总结 我们证明了给定有界模型平滑度下,模型的多样性和对抗样本可迁移性之间的相关性,基于此,我们提出了强大的正则化器,该正则化器对集成模型实现了针对现有强攻击的最佳稳健性。

  8. 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
    [会议版论文]   [完整版论文]   [代码]   [幻灯片]  
    @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},
    }

    关键词: 机器学习攻防

    总结 我们系统地分析了指导 DNN 的黑盒攻击的梯度估计器,它揭示了几个关键因素,这些因素可以用更少的查询实现更准确的梯度估计。实现这些关键因素的一种方法是对特定分辨率的图像进行梯度估计以生成攻击样本,基于此,我们提出的 PSBA 方法实现了目前为止最佳的攻击效率。

  9. 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
    [会议版论文]   [完整版论文]   [代码]   [幻灯片]  
    @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)}
    }

    关键词: 可验证机器学习

    总结 旋转和缩放等变换在自然世界中很常见。 我们提出了第一个基于随机平滑、严格的 Lipschitz 分析和分层抽样的针对自然变换的高效稳健性验证方法。 我们首次在大规模 ImageNet 数据集上实现了较高的可验证稳健性(> 30% 的可验证稳健分类准确率)。

  10. 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
    [会议版论文]   [完整版论文]   [代码]  
    @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},
    }

    关键词: 机器学习攻防

    总结 我们从理论上分析了使用非线性投影进行基于黑盒梯度估计的攻击效率,这表明适当的非线性投影可以帮助提高攻击效率。

  11. 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
    [论文]   [视频]  
    @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}
    }

    关键词: 机器学习与软件测试

    总结 我们提出了一种高效的流水线,通过对自然语言描述的测试步骤进行聚类,以生成可执行的测试用例,已部署用于微信测试。

  12. 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
    [论文]   [代码]  
    @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}
    }

    关键词: 可验证机器学习

    总结 我们提出了一种通过仅在联合训练模型的参考对抗空间内进行正则化来实现可验证稳健性的训练方法,以减轻优化难度并获得更高的可验证稳健性。

(*表示共同第一作者)

    2023

  1. Linyi Li
    Certifiably Trustworthy Deep Learning Systems at Scale
    Doctoral Thesis
    [完整版论文]  
    @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}
    }
  2. Zhangheng Li, Tianlong Chen, Linyi Li, Bo Li, Zhangyang Wang
    Can Pruning Improve Certified Robustness of Neural Networks?
    Transactions on Machine Learning Research (TMLR), 2023
    [完整版论文]  
    @article{
    li2023can,
    title={Can Pruning Improve Certified Robustness of Neural Networks?},
    author={Zhangheng LI and Tianlong Chen and Linyi Li and Bo Li and Zhangyang Wang},
    journal={Transactions on Machine Learning Research},
    issn={2835-8856},
    year={2023},
    url={https://openreview.net/forum?id=6IFi2soduD},
    }

    关键词: 可验证机器学习 模型剪枝

  3. Linyi Li, Tao Xie, Bo Li
    SoK: Certified Robustness for Deep Neural Networks
    44th IEEE Symposium on Security and Privacy (SP 2023)
    [完整版论文]   [会议版论文]   [幻灯片]   [代码]   [SOTA排行榜]  
    @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},
    }

    关键词: 可验证机器学习

  4. 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)
    [完整版论文]   [会议版论文]   [幻灯片]   [代码]  
    @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},
    }

    关键词: 可验证机器学习 数值可靠性

  5. Jiawei Zhang, Linyi Li, Ce Zhang, Bo Li
    CARE: Certifiably Robust Learning with Reasoning via Variational Inference
    First IEEE Conference on Secure and Trustworthy Machine Learning (SatML 2023)
    [完整版论文]   [会议版论文]  
    @inproceedings{
    zhang2023care,
    title={{CARE}: Certifiably Robust Learning with Reasoning via Variational Inference},
    author={Jiawei Zhang and Linyi Li and Ce Zhang and Bo Li},
    booktitle={First IEEE Conference on Secure and Trustworthy Machine Learning},
    year={2023},
    url={https://openreview.net/forum?id=1n6oWTTV1n}
    }

    关键词: 可验证机器学习 推理

  6. Mintong Kang, Linyi Li, Bo Li
    FaShapley: Fast and Approximated Shapley Based Model Pruning Towards Certifiably Robust DNNs
    First IEEE Conference on Secure and Trustworthy Machine Learning (SatML 2023)
    [会议版论文]  
    @inproceedings{
    kang2023fashapley,
    title={FaShapley: Fast and Approximated Shapley Based Model Pruning Towards Certifiably Robust {DNN}s},
    author={Mintong Kang and Linyi Li and Bo Li},
    booktitle={First IEEE Conference on Secure and Trustworthy Machine Learning},
    year={2023},
    url={https://openreview.net/forum?id=mJF9_Fs52ut}
    }

    关键词: 可验证机器学习 模型剪枝

  7. 2022

  8. 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
    [完整版论文]   [会议版论文]   [代码]   [海报]  
    @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}
    }

    关键词: 可验证机器学习 公平性

  9. Xiaojun Xu, Linyi Li, Bo Li
    LOT: Layer-wise Orthogonal Training on Improving \(\ell_2\) Certified Robustness
    Advances in Neural Information Processing Systems (NeurIPS) 2022
    [完整版论文]   [会议版论文]   [代码]  
    @inproceedings{xu2022lot,
    title = {LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness},
    author = {Xiaojun Xu and Linyi Li and Bo Li},
    booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
    year = {2022}
    }

    关键词: 可验证机器学习

  10. Bhaskar Ray Chaudhury, Linyi Li, Mintong Kang, Bo Li, Ruta Mehta
    Fairness in Federated Learning via Core-Stability
    Advances in Neural Information Processing Systems (NeurIPS) 2022
    [完整版论文]   [会议版论文]   [代码]   [海报]  
    @inproceedings{bhaskar2022fairness,
    title = {Fairness in Federated Learning via Core-Stability},
    author = {Bhaskar Ray Chaudhury and Linyi Li and Mintong Kang and Bo Li and Ruta Mehta},
    booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
    year = {2022}
    }

    关键词: 公平性

  11. Huan Zhang*, Shiqi Wang*, Kaidi Xu*, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter
    General Cutting Planes for Bound-Propagation-Based Neural Network Verification
    Advances in Neural Information Processing Systems (NeurIPS) 2022
    [完整版论文]   [会议版论文]   [代码]   [海报]  
    @inproceedings{zhang2022general,
    title = {General Cutting Planes for Bound-Propagation-Based Neural Network Verification},
    author = {Huan Zhang and Shiqi Wang and Kaidi Xu and Linyi Li and Bo Li and Suman Jana and Cho-Jui Hsieh and J. Zico Kolter},
    booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
    year = {2022}
    }

    关键词: 可验证机器学习

  12. Zhuolin Yang*, Zhikuan Zhao*, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlaš, Ji Liu, Heng Guo, Ce Zhang, Bo Li
    Improving Certified Robustness via Statistical Learning with Logical Reasoning
    Advances in Neural Information Processing Systems (NeurIPS) 2022
    [完整版论文]   [会议版论文]   [代码]  
    @inproceedings{yang2022improving,
    title = {Improving Certified Robustness via Statistical Learning with Logical Reasoning},
    author = {Zhuolin Yang and Zhikuan Zhao and Boxin Wang and Jiawei Zhang and Linyi Li and Hengzhi Pei and Bojan Karlaš and Ji Liu and Heng Guo and Ce Zhang and Bo Li},
    booktitle = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)},
    year = {2022}
    }

    关键词: 可验证机器学习 推理

  13. Hanjiang Hu, Zuxin Liu, Linyi Li, Jiacheng Zhu, Ding Zhao
    Robustness Certification of Visual Perception Models via Camera Motion Smoothing
    6th Annual Conference on Robot Learning (CoRL 2022)
    [论文]   [论坛]   [代码]  
    @inproceedings{
    hu2022robustness,
    title={Robustness Certification of Visual Perception Models via Camera Motion Smoothing},
    author={Hanjiang Hu and Zuxin Liu and Linyi Li and Jiacheng Zhu and Ding Zhao},
    booktitle={6th Annual Conference on Robot Learning},
    year={2022},
    url={https://openreview.net/forum?id=uUxDTZK3o3X}
    }

    关键词: 可验证机器学习

  14. Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
    Double Sampling Randomized Smoothing
    39th International Conference on Machine Learning (ICML 2022)
    [会议版论文]   [完整版论文]   [代码]  
    @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},
    }

    关键词: 可验证机器学习

  15. Wenda Chu, Linyi Li, Bo Li
    TPC: Transformation-Specific Smoothing for Point Cloud Models
    39th International Conference on Machine Learning (ICML 2022)
    [完整版论文]   [代码]  
    @inproceedings{
    chu2022tpc,
    title={TPC: Transformation-Specific Smoothing for Point Cloud Models},
    author={Wenda Chu and Linyi Li and Bo Li},
    booktitle={39th International Conference on Machine Learning (ICML 2022)},
    year={2022},
    }

    关键词: 可验证机器学习

  16. Maurice Weber, Linyi Li, Boxin Wang, Zhikuan Zhao, Bo Li, Ce Zhang
    Certifying Out-of-Domain Generalization for Blackbox Functions
    39th International Conference on Machine Learning (ICML 2022)
    [会议版论文]   [完整版论文]   [代码]  
    @inproceedings{
    weber2022certifying,
    title={Certifying Out-of-Domain Generalization for Blackbox Functions},
    author={Maurice Weber and Linyi Li and Boxin Wang and Zhikuan Zhao and Bo Li and Ce Zhang},
    booktitle={39th International Conference on Machine Learning (ICML 2022)},
    year={2022},
    }

    关键词: 可验证机器学习

  17. 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)
    [会议版论文]   [完整版论文]   [SOTA排行榜]   [代码]  
    @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}
    }

    关键词: 可验证机器学习 深度强化学习

  18. 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)
    [会议版论文]   [完整版论文]   [代码]  
    @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}
    }

    关键词: 可验证机器学习

  19. Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li
    CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
    10th International Conference on Learning Representations (ICLR 2022)
    [会议版论文]   [完整版论文]   [SOTA排行榜]   [代码]  
    @inproceedings{
    wu2022crop,
    title={{CROP}: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing},
    author={Fan Wu and Linyi Li and Zijian Huang and Yevgeniy Vorobeychik and Ding Zhao and Bo Li},
    booktitle={International Conference on Learning Representations},
    year={2022},
    url={https://openreview.net/forum?id=HOjLHrlZhmx}
    }

    关键词: 可验证机器学习 深度强化学习

  20. Ripon Saha, Akira Ura, Sonal Mahajan, Chenguang Zhu, Linyi Li, Yang Hu, Hiroaki Yoshida, Sarfraz Khurshid, Mukul R. Prasad
    SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
    44th International Conference on Software Engineering (ICSE 2022)
    [会议版论文]   [完整版论文]  
    @inproceedings{saha2022sapientml,
    title={SapientML: synthesizing machine learning pipelines by learning from human-written solutions},
    author={Ripon Saha, Akira Ura, Sonal Mahajan, Chenguang Zhu, Linyi Li, Yang Hu, Hiroaki Yoshida, Sarfraz Khurshid, Mukul R. Prasad},
    booktitle={2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)},
    year={2022},
    organization={IEEE}
    }

    关键词: 自动机器学习

  21. 2021

  22. 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
    [会议版论文]   [完整版论文]   [代码]  
    @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}
    }

    关键词: 鲁棒机器学习

  23. 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
    [会议版论文]   [完整版论文]   [代码]   [幻灯片]  
    @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},
    }

    关键词: 机器学习攻防

  24. 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
    [会议版论文]   [完整版论文]   [代码]   [幻灯片]  
    @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)}
    }

    关键词: 可验证机器学习

  25. 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
    [会议版论文]   [完整版论文]   [代码]  
    @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},
    }

    关键词: 机器学习攻防

  26. 2020

  27. 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
    [论文]   [视频]  
    @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}
    }

    关键词: 机器学习与软件测试

  28. 2019

  29. 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
    [论文]   [代码]  
    @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}
    }

    关键词: 可验证机器学习

  30. 2018

  31. Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson, Linyi Li
    Influence-Directed Explanations for Deep Convolutional Networks
    IEEE International Test Conference (ITC) 2018
    [论文]  
    @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},
    }

    关键词: 可解释机器学习 本科科研

  32. 2017

  33. Junyi Wang, Xiaoying Bai, Linyi Li, Zhicheng Ji, Haoran Ma
    A Model-Based Framework For Cloud API Testing
    IEEE 41st Annual Computer Software and Applications Conference (COMPSAC) 2017
    [论文]  
    @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},
    }

    关键词: 软件测试 本科科研

  34. Junyi Wang, Xiaoying Bai, Haoran Ma, Linyi Li, Zhicheng Ji
    Cloud API Testing
    IEEE International Conference on Software Verification and Validation Workshops (ICSTW) 2017
    [论文]  
    @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}
    }

    关键词: 软件测试 本科科研

Preprints can be found in Google Scholar profile.

其他

  • 我喜欢旅行、地理、语言学尤其是中文音韵学。我敬仰赵元任先生
  • 我有时会参加编程比赛。
  • 我非常喜欢吃辣🌶🌶🌶。
  • 我在张家界出生并度过童年,然后在长沙度过少年。
  • 我是土家族。土家语:Ngaf Bifzivkar.
更新日期:2024 年 08 月 14 日