Ahmed Salem

Senior Researcher

论文与出版物

查看方式：

- SpecGuard: Inference-Time Backdoor Detection For Free
  
  Wen Rui, Ahmed Salem, Andrew Paverd, M. Russinovich, Li Zheng
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
  
  Jun-Lin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du
  
  2026 NeurIPS | July 2026
  
  Publication Publication
- Sociocultural and psychological influences on Egyptian maritime students’ well-being and academic performance: implications for maritime education and training (MET)
  
  Ahmed Salem, M. Hassan
  
  Maritime Research and Technology | June 2026
  
  Publication
- 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
- Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database
  
  Aya A. S. Salem, Adam Y Ali, Layla Ali, H. Wolfson, Ahmed Salem, Sydney Hou, A. Mihalic, Michael S Wong
  
  Cureus | April 2026, 第 18 卷
  
  Publication Publication Publication
- Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells
  
  Sa′ed Rawashdea, M. Almajali, Ahmed Salem, Akram E. Zeid, Nathan Kawansson, D. Paterson
  
  ScienceDirect | April 2026
  
  DOI
- Advanced Microstructural Engineering of Gas Diffusion Layers for Synergistic Electrochemical Performance and Durability
  
  Sa′ed Alrwashdeh, Ahmed Salem
  
  HighTech and Innovation Journal | March 2026, 第 7 卷(1)
  
  DOI
- Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
  
  Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
  
  2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) | February 2026, pp. 85-102
  
  Publication Publication
- Examining Medicare Reimbursement Differences for Cochlear Implant Surgery
  
  Layla Ali, Samuel Salib, Iyawnna Hazzard, J. Howard, Cameron Ostroot, Ahmed Salem, Richard S. Isaacs
  
  Cureus | December 2025, 第 17 卷
  
  Publication Publication
- Do LLMs Comply Differently During Tests? And Can We Steer That?
  
  Sahar Abdelnabi, Ahmed Salem
  
  NeurIPS 2025 | October 2025
  
  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
- The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification
  
  Ahmed M. Khalifa, Mostafa Abdulaziz, Syed Shahzil Parvez, Ahmed Salem, Hafsa S Panhwer, Usman Saleem, Mahmoud Eldeeb, Tariq Weld-Ali, Maryam Mosaad
  
  Cureus | October 2025, 第 17 卷
  
  Publication 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
- Hey, That’s My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
  
  Mark Russinovich, Ahmed Salem, Yanan Cai
  
  ICLR 2026 | July 2024
  
  DOI Publication
- Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
  
  Edoardo Debenedetti, Javier Rando, Daniel Paleka, Fineas Silaghi, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Ahmed Salem, Rui Wen, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramer, Sahar Abdelnabi, Lea Schönherr
  
  NeurIPS 2024 | June 2024
  
  Preprint 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
- Two-in-One: A Model Hijacking Attack Against Text Generation Models
  
  Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
  
  USENIX Security Symposium | July 2023
  
  Publication
- UnGANable: Defending Against GAN-based Face Manipulation
  
  Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
  
  USENIX Security Symposium | July 2023
  
  Publication
- Analyzing Leakage of Personally Identifiable Information in Language Models
  
  Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 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

- SpecGuard: Inference-Time Backdoor Detection For Free
  
  Wen Rui, Ahmed Salem, Andrew Paverd, M. Russinovich, Li Zheng
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
  
  Jun-Lin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du
  
  2026 NeurIPS | July 2026
  
  Publication Publication
- Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
  
  Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
  
  2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) | February 2026, pp. 85-102
  
  Publication Publication
- The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification
  
  Ahmed M. Khalifa, Mostafa Abdulaziz, Syed Shahzil Parvez, Ahmed Salem, Hafsa S Panhwer, Usman Saleem, Mahmoud Eldeeb, Tariq Weld-Ali, Maryam Mosaad
  
  Cureus | October 2025, 第 17 卷
  
  Publication Publication
- Do LLMs Comply Differently During Tests? And Can We Steer That?
  
  Sahar Abdelnabi, Ahmed Salem
  
  NeurIPS 2025 | October 2025
  
  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
- Hey, That’s My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
  
  Mark Russinovich, Ahmed Salem, Yanan Cai
  
  ICLR 2026 | July 2024
  
  DOI Publication
- Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
  
  Edoardo Debenedetti, Javier Rando, Daniel Paleka, Fineas Silaghi, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Ahmed Salem, Rui Wen, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramer, Sahar Abdelnabi, Lea Schönherr
  
  NeurIPS 2024 | June 2024
  
  Preprint 项目
- Two-in-One: A Model Hijacking Attack Against Text Generation Models
  
  Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
  
  USENIX Security Symposium | July 2023
  
  Publication
- UnGANable: Defending Against GAN-based Face Manipulation
  
  Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
  
  USENIX Security Symposium | July 2023
  
  Publication
- 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
- Analyzing Leakage of Personally Identifiable Information in Language Models
  
  Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 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
- Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
  
  Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
  
  2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) | February 2026, pp. 85-102
  
  Publication Publication
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
  
  Jun-Lin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du
  
  2026 NeurIPS | July 2026
  
  Publication Publication
- SpecGuard: Inference-Time Backdoor Detection For Free
  
  Wen Rui, Ahmed Salem, Andrew Paverd, M. Russinovich, Li Zheng
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
  
  Jun-Lin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du
  
  2026 NeurIPS | July 2026
  
  Publication Publication
- 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
- Advanced Microstructural Engineering of Gas Diffusion Layers for Synergistic Electrochemical Performance and Durability
  
  Sa′ed Alrwashdeh, Ahmed Salem
  
  HighTech and Innovation Journal | March 2026, 第 7 卷(1)
  
  DOI
- 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
- Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
  
  Edoardo Debenedetti, Javier Rando, Daniel Paleka, Fineas Silaghi, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Ahmed Salem, Rui Wen, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramer, Sahar Abdelnabi, Lea Schönherr
  
  NeurIPS 2024 | June 2024
  
  Preprint 项目
- Two-in-One: A Model Hijacking Attack Against Text Generation Models
  
  Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
  
  USENIX Security Symposium | July 2023
  
  Publication
- UnGANable: Defending Against GAN-based Face Manipulation
  
  Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
  
  USENIX Security Symposium | July 2023
  
  Publication
- 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
- Analyzing Leakage of Personally Identifiable Information in Language Models
  
  Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 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
- Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database
  
  Aya A. S. Salem, Adam Y Ali, Layla Ali, H. Wolfson, Ahmed Salem, Sydney Hou, A. Mihalic, Michael S Wong
  
  Cureus | April 2026, 第 18 卷
  
  Publication Publication Publication
- Examining Medicare Reimbursement Differences for Cochlear Implant Surgery
  
  Layla Ali, Samuel Salib, Iyawnna Hazzard, J. Howard, Cameron Ostroot, Ahmed Salem, Richard S. Isaacs
  
  Cureus | December 2025, 第 17 卷
  
  Publication Publication
- The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification
  
  Ahmed M. Khalifa, Mostafa Abdulaziz, Syed Shahzil Parvez, Ahmed Salem, Hafsa S Panhwer, Usman Saleem, Mahmoud Eldeeb, Tariq Weld-Ali, Maryam Mosaad
  
  Cureus | October 2025, 第 17 卷
  
  Publication Publication
- Examining Medicare Reimbursement Differences for Cochlear Implant Surgery
  
  Layla Ali, Samuel Salib, Iyawnna Hazzard, J. Howard, Cameron Ostroot, Ahmed Salem, Richard S. Isaacs
  
  Cureus | December 2025, 第 17 卷
  
  Publication Publication
- Sociocultural and psychological influences on Egyptian maritime students’ well-being and academic performance: implications for maritime education and training (MET)
  
  Ahmed Salem, M. Hassan
  
  Maritime Research and Technology | June 2026
  
  Publication
- Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database
  
  Aya A. S. Salem, Adam Y Ali, Layla Ali, H. Wolfson, Ahmed Salem, Sydney Hou, A. Mihalic, Michael S Wong
  
  Cureus | April 2026, 第 18 卷
  
  Publication Publication Publication
- Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells
  
  Sa′ed Rawashdea, M. Almajali, Ahmed Salem, Akram E. Zeid, Nathan Kawansson, D. Paterson
  
  ScienceDirect | April 2026
  
  DOI
- Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells
  
  Sa′ed Rawashdea, M. Almajali, Ahmed Salem, Akram E. Zeid, Nathan Kawansson, D. Paterson
  
  ScienceDirect | April 2026
  
  DOI

- Sociocultural and psychological influences on Egyptian maritime students’ well-being and academic performance: implications for maritime education and training (MET)
  
  Ahmed Salem, M. Hassan
  
  Maritime Research and Technology | June 2026
  
  Publication
- Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database
  
  Aya A. S. Salem, Adam Y Ali, Layla Ali, H. Wolfson, Ahmed Salem, Sydney Hou, A. Mihalic, Michael S Wong
  
  Cureus | April 2026, 第 18 卷
  
  Publication Publication Publication
- Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells
  
  Sa′ed Rawashdea, M. Almajali, Ahmed Salem, Akram E. Zeid, Nathan Kawansson, D. Paterson
  
  ScienceDirect | April 2026
  
  DOI
- Advanced Microstructural Engineering of Gas Diffusion Layers for Synergistic Electrochemical Performance and Durability
  
  Sa′ed Alrwashdeh, Ahmed Salem
  
  HighTech and Innovation Journal | March 2026, 第 7 卷(1)
  
  DOI
- Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
  
  Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
  
  2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) | February 2026, pp. 85-102
  
  Publication Publication
- Examining Medicare Reimbursement Differences for Cochlear Implant Surgery
  
  Layla Ali, Samuel Salib, Iyawnna Hazzard, J. Howard, Cameron Ostroot, Ahmed Salem, Richard S. Isaacs
  
  Cureus | December 2025, 第 17 卷
  
  Publication Publication
- The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification
  
  Ahmed M. Khalifa, Mostafa Abdulaziz, Syed Shahzil Parvez, Ahmed Salem, Hafsa S Panhwer, Usman Saleem, Mahmoud Eldeeb, Tariq Weld-Ali, Maryam Mosaad
  
  Cureus | October 2025, 第 17 卷
  
  Publication 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
- VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
  
  Jun-Lin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du
  
  2026 NeurIPS | July 2026
  
  Publication Publication
- Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
  
  Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
  
  2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) | February 2026, pp. 85-102
  
  Publication Publication
- Do LLMs Comply Differently During Tests? And Can We Steer That?
  
  Sahar Abdelnabi, Ahmed Salem
  
  NeurIPS 2025 | October 2025
  
  Publication
- Hey, That’s My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
  
  Mark Russinovich, Ahmed Salem, Yanan Cai
  
  ICLR 2026 | July 2024
  
  DOI Publication
- Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
  
  Edoardo Debenedetti, Javier Rando, Daniel Paleka, Fineas Silaghi, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Ahmed Salem, Rui Wen, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramer, Sahar Abdelnabi, Lea Schönherr
  
  NeurIPS 2024 | June 2024
  
  Preprint 项目
- Two-in-One: A Model Hijacking Attack Against Text Generation Models
  
  Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem
  
  USENIX Security Symposium | July 2023
  
  Publication
- UnGANable: Defending Against GAN-based Face Manipulation
  
  Zheng Li, Ning Yu, Ahmed Salem, Michael Backes, Mario Fritz, Yang Zhang
  
  USENIX Security Symposium | July 2023
  
  Publication
- 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
- Analyzing Leakage of Personally Identifiable Information in Language Models
  
  Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin
  
  IEEE Symposium on Security and Privacy | May 2023
  
  Publication PDF DOI 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
- SpecGuard: Inference-Time Backdoor Detection For Free
  
  Wen Rui, Ahmed Salem, Andrew Paverd, M. Russinovich, Li Zheng
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- 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

Ahmed Salem

论文与出版物

SpecGuard: Inference-Time Backdoor Detection For Free

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Sociocultural and psychological influences on Egyptian maritime students’ well-being and academic performance: implications for maritime education and training (MET)

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

Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database

Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells

Advanced Microstructural Engineering of Gas Diffusion Layers for Synergistic Electrochemical Performance and Durability

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Examining Medicare Reimbursement Differences for Cochlear Implant Surgery

Do LLMs Comply Differently During Tests? And Can We Steer That?

Permissive Information-Flow Analysis for Large Language Models

The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification

Securing AI Agents with Information-Flow Control

Hey, That’s My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Bayesian Estimation of Differential Privacy

Two-in-One: A Model Hijacking Attack Against Text Generation Models

UnGANable: Defending Against GAN-based Face Manipulation

Analyzing Leakage of Personally Identifiable Information in Language Models

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

SpecGuard: Inference-Time Backdoor Detection For Free

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification

Do LLMs Comply Differently During Tests? And Can We Steer That?

Permissive Information-Flow Analysis for Large Language Models

Securing AI Agents with Information-Flow Control

Hey, That’s My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Two-in-One: A Model Hijacking Attack Against Text Generation Models

UnGANable: Defending Against GAN-based Face Manipulation

Bayesian Estimation of Differential Privacy

Analyzing Leakage of Personally Identifiable Information in Language Models

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

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

SpecGuard: Inference-Time Backdoor Detection For Free

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

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

Advanced Microstructural Engineering of Gas Diffusion Layers for Synergistic Electrochemical Performance and Durability

Permissive Information-Flow Analysis for Large Language Models

Securing AI Agents with Information-Flow Control

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Two-in-One: A Model Hijacking Attack Against Text Generation Models

UnGANable: Defending Against GAN-based Face Manipulation

Bayesian Estimation of Differential Privacy

Analyzing Leakage of Personally Identifiable Information in Language Models

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

Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database

Examining Medicare Reimbursement Differences for Cochlear Implant Surgery

The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification

Examining Medicare Reimbursement Differences for Cochlear Implant Surgery

Sociocultural and psychological influences on Egyptian maritime students’ well-being and academic performance: implications for maritime education and training (MET)

Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database

Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells

Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells

Sociocultural and psychological influences on Egyptian maritime students’ well-being and academic performance: implications for maritime education and training (MET)

Dermatology Match Trends From 2022–2025 Using the Texas Seeking Transparency in Application to Residency Database

Exergy-based pore-network optimization of gas diffusion layers for enhanced efficiency in proton exchange membrane fuel cells

Advanced Microstructural Engineering of Gas Diffusion Layers for Synergistic Electrochemical Performance and Durability

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Examining Medicare Reimbursement Differences for Cochlear Implant Surgery

The Digital Revolution in Cardiac Ischemia: Artificial Intelligence (AI)-Enhanced Detection, Diagnosis, and Risk Stratification

Permissive Information-Flow Analysis for Large Language Models

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Do LLMs Comply Differently During Tests? And Can We Steer That?

Hey, That’s My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Two-in-One: A Model Hijacking Attack Against Text Generation Models

UnGANable: Defending Against GAN-based Face Manipulation

Bayesian Estimation of Differential Privacy

Analyzing Leakage of Personally Identifiable Information in Language Models

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

SpecGuard: Inference-Time Backdoor Detection For Free

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

Securing AI Agents with Information-Flow Control