Ergute Bao (Bob)

A clearer and better photo

I am a Postdoc in Inria, working with PETSCRAFT team. Previously, I obtained PhD in CS from National University of Singapore (NUS), supervised by Xiaokui Xiao. Previously, I obtained BSc in CS from the Chinese University of Hong Kong (CUHK). I also used to work as a postdoc in MBZUAI, and as a research intern in Alibaba Group and SEA AI Lab. My CV.

Research: I am interested in establishing rigorous practices for private and secure AI:

• identifying risks in existing systems,
• formalizing these problems,
• studying them towards creating practical solutions with rigorous guarantees.

Selected Publications: [Google Scholar] [DBLP]

1. Distributed and Private Textual Data Synthesis from Embeddings.
   E. Bao, Hongyan Chang, Ali Shahin Shamsabadi, Ting Yu, and Xiaokui Xiao.
   Privacy Enhancing Technologies Symposium (PETS), 2027
2. GeoDPZO: Symmetry-Aware DP Zeroth-Order Optimization for Efficient LLM Fine-Tuning.
   Haichao Sha, Zihao Wang, Yuncheng Wu, E. Bao, Cuiping Li, and Hong Chen.
   Network and Distributed System Security Symposium (NDSS), 2027.
3. Auditing Apple’s DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, Practical Risks.
   Rishav Chourasia, E. Bao, Uzair Javaid, and Xiaokui Xiao.
   IEEE Symposium on Security and Privacy (S&P), 2026. Technical report.
   Distinguished paper award
4. Private Direct Preference Optimization for LLM Alignment.
   Yangfan Jiang, Fei Wei, E. Bao, Yaliang Li, Bolin Ding, and Xiaokui Xiao.
   ACM SIGSAC Conference on Computer and Communications Security (CCS), 2026. Technical report.
5. Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems.
   Hongyan Chang, E. Bao, Xinjian Luo, and Ting Yu.
   USENIX Conference on Security Symposium (USENIX Security), 2026. Technical report.
6. SaGD: A Node-Level Private Graph Learning Framework with Sensitivity-Aware Gradient Descent.
   Jianxin Wei, E. Bao, Xiaokui Xiao, and Ting Yu.
   The Web Conference (WWW), 2026.
7. Accurate Table Question Answering with Accessible LLMs.
   Yangfan Jiang, Fei Wei, E. Bao, Yaliang Li, Bolin Ding, Yin Yang, and Xiaokui Xiao.
   In IEEE International Conference on Data Engineering (ICDE), 2026.
8. Unlocking the Power of Differentially Private Zeroth-order Optimization for Fine-tuning LLMs.
   E. Bao, Yangfan Jiang, Fei Wei, Xiaokui Xiao, Zitao Li, Yaliang Li, and Bolin Ding
   USENIX Conference on Security Symposium (USENIX Security), 2025. Technical report. Erratum.
9. Towards Learning on Vertically Partitioned Data with Distributed Differential Privacy.
   E. Bao, Fei Wei, Xiaokui Xiao, Yin Yang, Tianyu Pang, and Chao Du
   IEEE International Conference on Data Engineering (ICDE), 2025. Technical report.
10. GCON: Differentially Private Graph Convolutional Network via Objective Perturbation.
    Jianxin Wei, Yizheng Zhu, Xiaokui Xiao, E. Bao, Yin Yang, Kuntai Cai, Beng Chin Ooi
    IEEE International Conference on Data Engineering (ICDE) 2025.
11. AAA: an Adaptive Mechanism for Locally Differential Private Mean Estimation.
    Fei Wei, E. Bao, Xiaokui Xiao, Yin Yang, and Bolin Ding.
    International Conference on Very Large Data Bases (PVLDB), 2024. Technical report.
12. Communication Efficient and Differentially Private Logistic Regression under the Distributed Setting.
    E. Bao, Dawei Gao, Xiaokui Xiao, and Yaliang Li.
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023.
13. Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
    E. Bao, Yizheng Zhu, Xiaokui Xiao, Yin Yang, Beng Chin Ooi, Benjamin H.M. Tan, and Khin M.M. Aung
    International Conference on Very Large Data Bases (PVLDB), 2022. Technical report.
14. DPIS: an Enhanced Mechanism for Differentially Private SGD with Importance Sampling
    Jianxin Wei, E. Bao, Xiaokui Xiao, and Yin Yang
    ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022.
15. CGM: An Enhanced Mechanism for Streaming Data Collection with Local Differential Privacy
    E. Bao, Yin Yang, Xiaokui Xiao, and Bolin Ding
    International Conference on Very Large Data Bases (PVLDB), 2021. Technical report.
16. Synthetic Data Generation with Differential Privacy via Bayesian Networks
    E. Bao, Xiaokui Xiao, Jun Zhao, Dongping Zhang, and Bolin Ding
    Journal of Privacy and Confidentiality (JPC), 2021, 11(3).
    Invited paper, based on our solution for 2018 NIST DP challenge.

Honors:

• IEEE S&P Distinguished Paper Award, 2026
  for the paper titled "Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks"
• Distinguished Reviewer in VLDB 2026
• 1st place in the 2020 NIST Differential Privacy Temporal Map Challenge
• 3rd place in the 2018 NIST Differential Privacy Synthetic Data Challenge

Services:

• I am/was a program committee member in:
  • ACM SIGMOD/PODS International Conference on Management of Data (SIGMOD): 2027
  • International Conference on Very Large Data Bases (VLDB): 2026 2027
  • IEEE International Conference on Data Engineering (ICDE): 2026
• I am/was a reviewer for:
  • The International Journal on Very Large Data Bases (VLDBJ)
  • IEEE Transactions on Knowledge and Data Engineering (TKDE)
  • ACM Transactions on Knowledge Discovery from Data (TKDD)
  • IEEE Transactions on Big Data (TBD)

Contact:

Email: baoergute8@gmail.com

Last updated: September 2026