李林翼

伊利諾大學尚佩恩校區資訊工程系博士。
[email protected]
[個人簡歷（英文版）]

我是李林翼，博士畢業於伊利諾大學尚佩恩校區資訊工程系。我的導師是李博教授，共同指導老師是謝濤教授。

我的研究方向為機器學習與資訊安全。 具體地，我專注於（1）構建可信深度學習系統，以實現針對噪聲的可驗證穩健性[IJCAI 2019] [ICLR 2022a] [ICML 2022a] [SP 2023]，針對語義性變換的可驗證穩健性[CCS 2021] [ICML 2022b]，針對訓練集擾動的可驗證穩健性[ICLR 2022b]，針對分佈偏移的可驗證穩健性[ICML 2022c]，可驗證公平性[NeurIPS 2022]，可驗證數值可靠性[ICSE 2023]等等。（2）以數據和系統性評估為中心的大模型研究。 我亦進行過集成模型的穩健性研究[NeurIPS 2021]，深度學習模型的黑盒攻擊研究[ICML 2021] [AISTATS 2021]，以及機器學習在軟體測試中的應用研究[FSE 2020 Industry]。 我有幸獲得Rising Stars in Data Science，AdvML Rising Star Award，和Wing Kai Cheng獎學金，並有幸入圍2022 Qualcomm Innovation Fellowship和2022 Two Sigma PhD Fellowship。

我2018年大學畢業於北京清華大學計算機科學與技術系。在白曉穎教授的指導下，我進行了Web API自動化測試方向的研究。

對可信機器學習/大模型的研究感興趣？歡迎研究合作與交流！在讀本科/碩士/博士學生：請以[seek for (position/collaboration)]為主題郵件聯繫我（[email protected]），匹配者可提供或推薦相應深造和實習機會。

研究成果

目前，我的研究主要針對
  1. 為給定的深度神經網絡模型提供各種可信屬性（魯棒性、公平性、可靠性等）的嚴格保證；
  2. 通過模型設計、數據集構建、模型訓練、後處理等提高這種機器學習的可信保證。
點擊以瀏覽細節。
（*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)
    [完整版論文]   [會議版論文]   [簡報]   [代碼]   [SOTA榜單]  
    @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},
    }

    關鍵詞： 可驗證機器學習

    總結 對 DNN 可驗證穩健性研究的全面系統總結，包括實踐和理論上的意義、發現、主要挑戰和未來方向的討論，以及一個開源統一工具箱來評估 20 多種代表性方法。

  • 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)
    [完整版論文]   [會議版論文]   [簡報]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習 數值可靠性

    總結 提出了RANUM：一種高效的白盒框架，適用於一般的人工神經網路模型，用於驗證數值可靠性（例如，不輸出NAN或INF）、面向缺陷觸發的系統測試生成和修復生成。其中，RANUM是後兩種任務的首個自動化框架。

  • 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
    [完整版論文]   [會議版論文]   [代碼]   [海報]  
    @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}
    }

    關鍵詞： 可驗證機器學習 公平性

    總結 一種新的實用且可擴展的驗證算法，當分佈從訓練偏移時，為給定模型提供公平性保證，基於統計亞群分解。

  • Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
    Double Sampling Randomized Smoothing
    39th International Conference on Machine Learning (ICML 2022)
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

    總結 對隨機平滑化方法的一種更緊的驗證算法，其首次利用來自兩種不同分佈的統計數據，來實現更緊的穩健性界，並在寬鬆條件下首次突破眾所周知的維數陷阱。

  • Wenda Chu, Linyi Li, Bo Li
    TPC: Transformation-Specific Smoothing for Point Cloud Models
    39th International Conference on Machine Learning (ICML 2022)
    [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

    總結 通過擴展對圖像分類模型的穩健性驗證算法，我們為點雲模型提供了最先進的關於幾何變換意義下的穩健性驗證算法，其核心思想基於對點雲幾何變換的解析性分析。

  • 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)
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

    總結 一種針對分佈偏移的模型泛化的高效驗證算法，它不需要對模型的架構進行假設，只要分佈偏移受 Hellinger 距離（一種f散度）的限制。核心方法基於 Gramian 矩陣的半正定性質。

  • 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)
    [會議版論文]   [完整版論文]   [SOTA榜單]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習 深度強化學習

    總結 通過聚合在分區數據集上訓練的策略和多重步驟下的策略，實現可驗證的深度強化學習對離線訓練數據集擾動（即荼毒攻擊）的穩健性。

  • 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)
    [會議版論文]   [完整版論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

    總結 基於隨機平滑分類器的曲率界，我們證明了大的分類概率差和梯度多樣性對於可驗證的穩健集成模型是充分必要的條件。通過約束這兩個因素，我們實現了目前為止最佳的 L2 範數擾動下的穩健性。

  • 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)
    [會議版論文]   [完整版論文]   [SOTA榜單]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習 深度強化學習

    總結 通過將隨機平滑化方法與一組基於軌蹟的搜索算法相結合，我們提出了第一個用於驗證深度強化學習對狀態擾動的穩健性的高效算法。

  • 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
    [會議版論文]   [完整版論文]   [代碼]  
    @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}
    }

    關鍵詞： 穩健機器學習

    總結 我們證明了給定有界模型平滑度下，模型的多樣性和對抗樣本可遷移性之間的相關性，基於此，我們提出了強大的正則化器，該正則化器對集成模型實現了針對現有強攻擊的最佳穩健性。

  • 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
    [會議版論文]   [完整版論文]   [代碼]   [簡報]  
    @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)}
    }

    關鍵詞： 可驗證機器學習

    總結 旋轉和縮放等變換在自然世界中很常見。我們提出了第一個基於隨機平滑、嚴格的 Lipschitz 分析和分層抽樣的針對自然變換的高效穩健性驗證方法。我們首次在大規模 ImageNet 數據集上實現了較高的可驗證穩健性（> 30% 的可驗證穩健分類準確率）。

  • 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
    [論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

    總結 我們提出了一種通過僅在聯合訓練模型的參考對抗空間內進行正則化來實現可驗證穩健性的訓練方法，以減輕優化難度並獲得更高的可驗證穩健性。

（*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)
    [完整版論文]   [會議版論文]   [簡報]   [代碼]   [SOTA榜單]  
    @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},
    }

    關鍵詞： 可驗證機器學習

    總結 對 DNN 可驗證穩健性研究的全面系統總結，包括實踐和理論上的意義、發現、主要挑戰和未來方向的討論，以及一個開源統一工具箱來評估 20 多種代表性方法。

  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)
    [完整版論文]   [會議版論文]   [簡報]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習 數值可靠性

    總結 提出了RANUM：一種高效的白盒框架，適用於一般的人工神經網路模型，用於驗證數值可靠性（例如，不輸出NAN或INF）、面向缺陷觸發的系統測試生成和修復生成。其中，RANUM是後兩種任務的首個自動化框架。

  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
    [完整版論文]   [會議版論文]   [代碼]   [海報]  
    @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}
    }

    關鍵詞： 可驗證機器學習 公平性

    總結 一種新的實用且可擴展的驗證算法，當分佈從訓練偏移時，為給定模型提供公平性保證，基於統計亞群分解。

  4. Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
    Double Sampling Randomized Smoothing
    39th International Conference on Machine Learning (ICML 2022)
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

    總結 對隨機平滑化方法的一種更緊的驗證算法，其首次利用來自兩種不同分佈的統計數據，來實現更緊的穩健性界，並在寬鬆條件下首次突破眾所周知的維數陷阱。

  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)
    [會議版論文]   [完整版論文]   [SOTA榜單]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習 深度強化學習

    總結 通過聚合在分區數據集上訓練的策略和多重步驟下的策略，實現可驗證的深度強化學習對離線訓練數據集擾動（即荼毒攻擊）的穩健性。

  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)
    [會議版論文]   [完整版論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

    總結 基於隨機平滑分類器的曲率界，我們證明了大的分類概率差和梯度多樣性對於可驗證的穩健集成模型是充分必要的條件。通過約束這兩個因素，我們實現了目前為止最佳的 L2 範數擾動下的穩健性。

  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
    [會議版論文]   [完整版論文]   [代碼]  
    @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}
    }

    關鍵詞： 穩健機器學習

    總結 我們證明了給定有界模型平滑度下，模型的多樣性和對抗樣本可遷移性之間的相關性，基於此，我們提出了強大的正則化器，該正則化器對集成模型實現了針對現有強攻擊的最佳穩健性。

  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
    [會議版論文]   [完整版論文]   [代碼]   [簡報]  
    @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},
    }

    關鍵詞： 機器學習攻擊與防禦

    總結 我們系統地分析了指導 DNN 的黑盒攻擊的梯度估計器，它揭示了幾個關鍵因素，這些因素可以用更少的查詢實現更準確的梯度估計。實現這些關鍵因素的一種方法是對特定解析度的圖像進行梯度估計以生成攻擊樣本，基於此，我們提出的 PSBA 方法實現了目前為止最佳的攻擊效率。

  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
    [會議版論文]   [完整版論文]   [代碼]   [簡報]  
    @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)}
    }

    關鍵詞： 可驗證機器學習

    總結 旋轉和縮放等變換在自然世界中很常見。我們提出了第一個基於隨機平滑、嚴格的 Lipschitz 分析和分層抽樣的針對自然變換的高效穩健性驗證方法。我們首次在大規模 ImageNet 數據集上實現了較高的可驗證穩健性（> 30% 的可驗證穩健分類準確率）。

  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
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 機器學習攻擊與防禦

    總結 我們從理論上分析了使用非線性投影進行基於黑盒梯度估計的攻擊效率，這表明適當的非線性投影可以幫助提高攻擊效率。

  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
    [論文]   [視頻]  
    @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}
    }

    關鍵詞： 機器學習與軟體測試

    總結 我們提出了一種高效的流水線，通過對自然語言描述的測試步驟進行聚類，以生成可執行的測試用例，已部署用於微信測試。

  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
    [論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

    總結 我們提出了一種通過僅在聯合訓練模型的參考對抗空間內進行正則化來實現可驗證穩健性的訓練方法，以減輕優化難度並獲得更高的可驗證穩健性。

（*表示共同第一作者）

    2023

  1. Linyi Li
    Certifiably Trustworthy Deep Learning Systems at Scale
    Doctoral Thesis
    [完整版論文]  
    @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
    [完整版論文]  
    @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},
    }

    關鍵詞： 可驗證機器學習 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)
    [完整版論文]   [會議版論文]   [簡報]   [代碼]   [SOTA榜單]  
    @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},
    }

    關鍵詞： 可驗證機器學習

  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)
    [完整版論文]   [會議版論文]   [簡報]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習 數值可靠性

  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)
    [完整版論文]   [會議版論文]  
    @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}
    }

    關鍵詞： 可驗證機器學習 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)
    [會議版論文]  
    @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}
    }

    關鍵詞： 可驗證機器學習 模型剪枝

    7. 2022

  7. 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
    [完整版論文]   [會議版論文]   [代碼]   [海報]  
    @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}
    }

    關鍵詞： 可驗證機器學習 公平性

  8. 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
    [完整版論文]   [會議版論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

  9. 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
    [完整版論文]   [會議版論文]   [代碼]   [海報]  
    @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}
    }

    關鍵詞： 公平性

  10. 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
    [完整版論文]   [會議版論文]   [代碼]   [海報]  
    @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}
    }

    關鍵詞： 可驗證機器學習

  11. 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
    [完整版論文]   [會議版論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習 推理

  12. 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)
    [論文]   [討論版]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

  13. Linyi Li, Jiawei Zhang, Tao Xie, Bo Li
    Double Sampling Randomized Smoothing
    39th International Conference on Machine Learning (ICML 2022)
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

  14. Wenda Chu, Linyi Li, Bo Li
    TPC: Transformation-Specific Smoothing for Point Cloud Models
    39th International Conference on Machine Learning (ICML 2022)
    [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

  15. 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)
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 可驗證機器學習

  16. 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)
    [會議版論文]   [完整版論文]   [SOTA榜單]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習 深度強化學習

  17. 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)
    [會議版論文]   [完整版論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

  18. 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)
    [會議版論文]   [完整版論文]   [SOTA榜單]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習 深度強化學習

  19. 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)
    [會議版論文]   [完整版論文]  
    @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}
    }

    關鍵詞： 自動機器學習

    20. 2021

  20. 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
    [會議版論文]   [完整版論文]   [代碼]  
    @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}
    }

    關鍵詞： 穩健機器學習

  21. 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
    [會議版論文]   [完整版論文]   [代碼]   [簡報]  
    @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},
    }

    關鍵詞： 機器學習攻擊與防禦

  22. 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
    [會議版論文]   [完整版論文]   [代碼]   [簡報]  
    @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)}
    }

    關鍵詞： 可驗證機器學習

  23. 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
    [會議版論文]   [完整版論文]   [代碼]  
    @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},
    }

    關鍵詞： 機器學習攻擊與防禦

    24. 2020

  24. 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
    [論文]   [視頻]  
    @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}
    }

    關鍵詞： 機器學習與軟體測試

    25. 2019

  25. 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
    [論文]   [代碼]  
    @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}
    }

    關鍵詞： 可驗證機器學習

    26. 2018

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

    關鍵詞： 可解釋機器學習 大學科研

    27. 2017

  27. 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
    [論文]  
    @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},
    }

    關鍵詞： 軟體測試 大學科研

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

    關鍵詞： 軟體測試 大學科研

Preprints can be found in Google Scholar profile.

其他

  • 我喜歡旅行、地理、語言學尤其是中文音韻學。我敬仰趙元任先生。

  • 我有時會參加編程大賽。

  • 我非常喜歡吃辣🌶🌶🌶。

  • 我在中國大陸的張家界出生並度過童年，然後在長沙度過少年。

  • 我是土家族。土家語：Ngaf Bifzivkar.

更新日期：2023 年 12 月 11 日