Selected Publications

• Linyi Li, Tao Xie, Bo Li. SoK: Certified Robustness for Deep Neural Networks. (IEEE Symposium on Security and Privacy (Oakland), 2022) [Leaderboard] [BibTeX]

  
  @article{li2020sok,
    title={Sok: Certified robustness for deep neural networks},
    author={Li, Linyi and Xie, Tao and Li, Bo},
    journal={(IEEE Symposium on Security and Privacy (Oakland)},
    year={2022}
  }

  This work provides a thorough taxonomy for the DNN robustness certification and training approaches, as well as an open-sourced unified platform to evaluate different certifiably robust approaches.

• Chejian Xu*, Wenhao Ding*, Weijie Lyu, Zuxin Liu, Shuai Wang, Yihan He, Hanjiang Hu, Ding Zhao, Bo Li. SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles. (NeurIPS, 2022) [Leaderboard] [BibTeX]

  
  @article{xu2022safebench,
    title={SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles},
    author={Xu, Chejian and Ding, Wenhao and Lyu, Weijie and Liu, Zuxin and Wang, Shuai and He, Yihan and Hu, Hanjiang and Zhao, Ding and Li, Bo},
    journal={NeurIPS},
    year={2022}
  }

  This work provides a unified platform to generate diverse safety-critical scenarios for efficient autonomous driving testing under different metrics.

• 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. (NeurIPS 2022) [BibTeX]

  
  @article{YangImp2022,
    title={Improving Certified Robustness via Statistical Learning with Logical Reasoning},
    author={Yang, Zhuolin and Zhao, Zhikuan and Wang, Boxin and Zhang, Jiawei and Li, Linyi and Pei, Hengzhi and Karlaš, Bojan and Liu, Ji and Guo, Heng and Zhang, Ce and Li, Bo},
    journal={NeurIPS},
    year={2022}
  }

  This work provides the first knowledge-enabled, certifiably robust ML pipeline, sensing-reasoning pipeline, by combining statistical learning with logical reasoning. It proves the robustness certification for a reasoning component such as MLN.

• Xiaojun Xu, Linyi Li, Bo Li. LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness. (NeurIPS 2022) [BibTeX]

  
  @article{XuLot2022,
    title={LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness},
    author={Xu, Xiaojun and Li, Linyi and Li, Bo},
    journal={NeurIPS},
    year={2022}
  }

  This work provides a layer-wise orthogonal training method (LOT) to effectively train 1-Lipschitz convolution layers and therefore provides high certified robustness for trained DNNs.

• Boxin Wang*, Chejian Xu*, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, Bo Li. Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models. (NeurIPS 2021, Oral presentation, 3.3% accepted rate) [Leaderboard] [BibTeX]

  @inproceedings{wang2021adversarial,
  title={Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models},
  author={Wang, Boxin and Xu, Chejian and Wang, Shuohang and Gan, Zhe and Cheng, Yu and Gao, Jianfeng and Awadallah, Ahmed Hassan and Li, Bo},
  booktitle={Advances in Neural Information Processing Systems},
  year={2021}
  }

  This work provides a comprehensive adversarial evaluation platform and benchmark for large language models via generating stealthy adversarial perturbations on texts using diverse attack methods in different spaces.

• Boxin Wang*, Fan Wu*, Yunhui Long*, Luka Rimanic, Ce Zhang, Bo Li. DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation. (CCS 2021) [BibTeX]

  @inproceedings{wang2021datalens,
  title={DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation},
  author={Wang, Boxin and Wu, Fan and Long, Yunhui and Rimanic, Luka and Zhang, Ce and Li, Bo},
  booktitle={Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security},
  year={2021}
  }

  This work provides the first scalable differentially private data generative model for high-dimensional data with convergence guarantees.

• Chulin Xie, Minghao Chen, Pin-Yu Chen, Bo Li. CRFL: Certifiably Robust Federated Learning against Backdoor Attacks. (ICML 2021) [BibTeX]

  @inproceedings{xie2021crfl,
  title={CRFL: Certifiably Robust Federated Learning against Backdoor Attacks},
  author={Xie, Chulin and Chen, Minghao and Chen, Pin-Yu and Li, Bo},
  booktitle={International Conference on Machine Learning},
  year={2021}
  }

  This work provides the first certifiably robust federated learning framework against adversarial agents, and the certification is guaranteed on the feature, instance, and agent levels.

• Kaizhao Liang*, Jacky Zhang*, Boxin Wang, Zhuolin Yang, Sanmi Koyejo, Bo Li. Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability. (ICML 2021) [BibTeX]

  @inproceedings{liang2021uncovering,
  title={Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability},
  author={Liang, Kaizhao and Zhang, Jacky and Wang, Boxin and Yang, Zhuolin and Koyejo, Sanmi and Li, Bo},
  booktitle={International Conference on Machine Learning},
  year={2021}
  }

  This work proves that adversarial transferability (robustness property) and domain transferability (generalization property) are bidirectional indicators of each other.