MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem
May 2026
Andrew Paverd
Principal Research Manager
出版物
-
-
-
-
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
-
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
-
-
-
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
-
-
-
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, 巻2023
-
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
2023 International Conference on Machine Learning | July 2023
編集者: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
-
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
2023 IEEE Symposium on Security and Privacy | May 2023
-
-
-
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
-
-
-
Grey-box Extraction of Natural Language Models
Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
International Conference on Machine Learning | July 2021
編集者: Marina Meila and Tong Zhang
-
-
-
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
-
-
-
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem
May 2026
-
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
-
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
-
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
-
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, 巻2023
-
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
2023 International Conference on Machine Learning | July 2023
編集者: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
-
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
2023 IEEE Symposium on Security and Privacy | May 2023
-
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
-
Grey-box Extraction of Natural Language Models
Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
International Conference on Machine Learning | July 2021
編集者: Marina Meila and Tong Zhang
-
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
-
-
-
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
-
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
-
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
-
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, 巻2023
-
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
2023 International Conference on Machine Learning | July 2023
編集者: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
-
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
2023 IEEE Symposium on Security and Privacy | May 2023
-
Grey-box Extraction of Natural Language Models
Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
International Conference on Machine Learning | July 2021
編集者: Marina Meila and Tong Zhang
-
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
-
-
-
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
Rui Wen, Mark Russinovich, Andrew Paverd, Jun Sakuma, Ahmed Salem
May 2026
-
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
-
-
-
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
-
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, 巻2023
-
-
-
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
-
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Ahmed Salem, Victor Ruehle, Andrew Paverd, Mohammad Naseri, Boris Köpf, Daniel Jones
2023 International Conference on Machine Learning | July 2023
編集者: Barbara Engelhardt, Emma Brunskill, Kyunghyun Cho
-
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
2023 IEEE Symposium on Security and Privacy | May 2023
-
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
-
Grey-box Extraction of Natural Language Models
Santiago Zanella-Béguelin, Shruti Tople, Andrew Paverd, Boris Köpf
International Conference on Machine Learning | July 2021
編集者: Marina Meila and Tong Zhang
-
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
-