Andrew Paverd

Principal Research Manager

论文与出版物

查看方式：

- MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
  
  Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Permissive Information-Flow Analysis for Large Language Models
  
  Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin
  
  Transactions on Machine Learning Research (TMLR) | October 2025
  
  Publication Publication 项目
- Securing AI Agents with Information-Flow Control
  
  Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  May 2025
  
  arXiv | May 2025
  
  DOI Publication Publication 项目项目
- Closed-Form Bounds for DP-SGD against Record-level Inference
  
  Giovanni Cherubin, Boris Köpf, Andrew Paverd, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  USENIX Security Symposium | August 2024
  
  Publication 项目
- On the Efficacy of Differentially Private Few-shot Image Classification
  
  Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Béguelin, Richard Turner, Antti Honkela
  
  Transactions on Machine Learning Research | December 2023, 第 2023 卷
  
  DOI Preprint Preprint Publication 项目
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  International Conference on Machine Learning | July 2023
  
  编辑: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication 项目
- SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
  
  Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 项目
- Pre-hijacked accounts: An Empirical Study of Security Failures in User Account Creation on the Web
  
  Avinash Sudhodanan, Andrew Paverd
  
  31st USENIX Security Symposium | August 2022
  
  Preprint
- Grey-box Extraction of Natural Language Models
  
  Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
  
  International Conference on Machine Learning | July 2021
  
  编辑: Marina Meila and Tong Zhang
  
  PDF 项目
- Analyzing Information Leakage of Updates to Natural Language Models
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Victor Ruehle, Andrew Paverd, Olga Ohrimenko, Boris Köpf, Marc Brockschmidt
  
  ACM Conference on Computer and Communication Security (CCS) | November 2020
  
  Author's Version 项目

- MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
  
  Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Permissive Information-Flow Analysis for Large Language Models
  
  Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin
  
  Transactions on Machine Learning Research (TMLR) | October 2025
  
  Publication Publication 项目
- Securing AI Agents with Information-Flow Control
  
  Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  May 2025
  
  arXiv | May 2025
  
  DOI Publication Publication 项目项目
- Closed-Form Bounds for DP-SGD against Record-level Inference
  
  Giovanni Cherubin, Boris Köpf, Andrew Paverd, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  USENIX Security Symposium | August 2024
  
  Publication 项目
- On the Efficacy of Differentially Private Few-shot Image Classification
  
  Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Béguelin, Richard Turner, Antti Honkela
  
  Transactions on Machine Learning Research | December 2023, 第 2023 卷
  
  DOI Preprint Preprint Publication 项目
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  International Conference on Machine Learning | July 2023
  
  编辑: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication 项目
- SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
  
  Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 项目
- Pre-hijacked accounts: An Empirical Study of Security Failures in User Account Creation on the Web
  
  Avinash Sudhodanan, Andrew Paverd
  
  31st USENIX Security Symposium | August 2022
  
  Preprint
- Grey-box Extraction of Natural Language Models
  
  Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
  
  International Conference on Machine Learning | July 2021
  
  编辑: Marina Meila and Tong Zhang
  
  PDF 项目
- Analyzing Information Leakage of Updates to Natural Language Models
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Victor Ruehle, Andrew Paverd, Olga Ohrimenko, Boris Köpf, Marc Brockschmidt
  
  ACM Conference on Computer and Communication Security (CCS) | November 2020
  
  Author's Version 项目
- Permissive Information-Flow Analysis for Large Language Models
  
  Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin
  
  Transactions on Machine Learning Research (TMLR) | October 2025
  
  Publication Publication 项目
- Securing AI Agents with Information-Flow Control
  
  Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  May 2025
  
  arXiv | May 2025
  
  DOI Publication Publication 项目项目
- Closed-Form Bounds for DP-SGD against Record-level Inference
  
  Giovanni Cherubin, Boris Köpf, Andrew Paverd, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  USENIX Security Symposium | August 2024
  
  Publication 项目
- On the Efficacy of Differentially Private Few-shot Image Classification
  
  Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Béguelin, Richard Turner, Antti Honkela
  
  Transactions on Machine Learning Research | December 2023, 第 2023 卷
  
  DOI Preprint Preprint Publication 项目
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  International Conference on Machine Learning | July 2023
  
  编辑: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication 项目
- SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
  
  Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 项目
- Grey-box Extraction of Natural Language Models
  
  Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
  
  International Conference on Machine Learning | July 2021
  
  编辑: Marina Meila and Tong Zhang
  
  PDF 项目
- Analyzing Information Leakage of Updates to Natural Language Models
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Victor Ruehle, Andrew Paverd, Olga Ohrimenko, Boris Köpf, Marc Brockschmidt
  
  ACM Conference on Computer and Communication Security (CCS) | November 2020
  
  Author's Version 项目

- MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
  
  Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Securing AI Agents with Information-Flow Control
  
  Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  May 2025
  
  arXiv | May 2025
  
  DOI Publication Publication 项目项目
- Permissive Information-Flow Analysis for Large Language Models
  
  Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin
  
  Transactions on Machine Learning Research (TMLR) | October 2025
  
  Publication Publication 项目
- On the Efficacy of Differentially Private Few-shot Image Classification
  
  Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Béguelin, Richard Turner, Antti Honkela
  
  Transactions on Machine Learning Research | December 2023, 第 2023 卷
  
  DOI Preprint Preprint Publication 项目
- Closed-Form Bounds for DP-SGD against Record-level Inference
  
  Giovanni Cherubin, Boris Köpf, Andrew Paverd, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  USENIX Security Symposium | August 2024
  
  Publication 项目
- Bayesian Estimation of Differential Privacy
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
  
  International Conference on Machine Learning | July 2023
  
  编辑: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
  
  Publication 项目
- SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
  
  Ahmed Salem, Giovanni Cherubin, David Evans, Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 项目
- Pre-hijacked accounts: An Empirical Study of Security Failures in User Account Creation on the Web
  
  Avinash Sudhodanan, Andrew Paverd
  
  31st USENIX Security Symposium | August 2022
  
  Preprint
- Grey-box Extraction of Natural Language Models
  
  Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
  
  International Conference on Machine Learning | July 2021
  
  编辑: Marina Meila and Tong Zhang
  
  PDF 项目
- Analyzing Information Leakage of Updates to Natural Language Models
  
  Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Victor Ruehle, Andrew Paverd, Olga Ohrimenko, Boris Köpf, Marc Brockschmidt
  
  ACM Conference on Computer and Communication Security (CCS) | November 2020
  
  Author's Version 项目

Andrew Paverd

论文与出版物

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs

Permissive Information-Flow Analysis for Large Language Models

Securing AI Agents with Information-Flow Control

Closed-Form Bounds for DP-SGD against Record-level Inference

On the Efficacy of Differentially Private Few-shot Image Classification

Bayesian Estimation of Differential Privacy

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Pre-hijacked accounts: An Empirical Study of Security Failures in User Account Creation on the Web

Grey-box Extraction of Natural Language Models

Analyzing Information Leakage of Updates to Natural Language Models

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs

Permissive Information-Flow Analysis for Large Language Models

Securing AI Agents with Information-Flow Control

Closed-Form Bounds for DP-SGD against Record-level Inference

On the Efficacy of Differentially Private Few-shot Image Classification

Bayesian Estimation of Differential Privacy

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Pre-hijacked accounts: An Empirical Study of Security Failures in User Account Creation on the Web

Grey-box Extraction of Natural Language Models

Analyzing Information Leakage of Updates to Natural Language Models

Permissive Information-Flow Analysis for Large Language Models

Securing AI Agents with Information-Flow Control

Closed-Form Bounds for DP-SGD against Record-level Inference

On the Efficacy of Differentially Private Few-shot Image Classification

Bayesian Estimation of Differential Privacy

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Grey-box Extraction of Natural Language Models

Analyzing Information Leakage of Updates to Natural Language Models

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs

Securing AI Agents with Information-Flow Control

Permissive Information-Flow Analysis for Large Language Models

On the Efficacy of Differentially Private Few-shot Image Classification

Closed-Form Bounds for DP-SGD against Record-level Inference

Bayesian Estimation of Differential Privacy

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Pre-hijacked accounts: An Empirical Study of Security Failures in User Account Creation on the Web

Grey-box Extraction of Natural Language Models

Analyzing Information Leakage of Updates to Natural Language Models