Ali Shahin Shamsabadi

63 papers A* 13A 4B 2Misc 3Journal 39Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies. CoRR Miles Brundage, Noemi Dreksler, Aidan Homewood, Sean McGregor, Patricia Paskov, Conrad Stosz, Girish Sastry, A. Feder Cooper, George Balston, Steven Adler, Stephen Casper, Markus Anderljung, Grace W. Lindsay, Sören Mindermann, Vasilios Mavroudis, Ben Bucknall, Charlotte Stix, Jonas Freund, Lorenzo Pacchiardi, José Hernández-Orallo, Matteo Pistillo, Michael Chen, Chris Painter, Dean W. Ball, Cullen O'Keefe, Gabriel Weil, Ben Harack, Graeme Finley, Ryan Hassan, Scott Emmons, Charles Foster, Anka Reuel, Bri Treece, Yoshua Bengio, Daniel Reti, Rishi Bommasani, Cristian Trout, Ali Shahin Shamsabadi, Rajiv Dattani, Adrian Weller, Robert Trager, Jaime Sevilla, Lauren Wagner, Lisa Soder, Ketan Ramakrishnan, Henry Papadatos, Malcolm Murray, Ryan Tovcimak
2026	J	`jnl`	SPILLage: Agentic Oversharing on the Web. CoRR Jaechul Roh, Eugene Bagdasarian, Hamed Haddadi, Ali Shahin Shamsabadi
2025	A*	`conf`	Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention. ICML Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese, Xiao Wang, Adrian Weller, Nicolas Papernot
2025	J	`jnl`	Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention. CoRR Stephan Rabanser, Ali Shahin Shamsabadi, Olive Franzese, Xiao Wang, Adrian Weller, Nicolas Papernot
2025	A*	`conf`	Context-Aware Membership Inference Attacks against Pre-trained Large Language Models. EMNLP Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Reza Shokri
2025	A*	`conf`	Membership and Memorization in LLM Knowledge Distillation. EMNLP Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu, Yifeng Cai, Hamed Haddadi
2025	J	`jnl`	Membership and Memorization in LLM Knowledge Distillation. CoRR Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu, Yifeng Cai, Hamed Haddadi
2025	J	`jnl`	NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation. CoRR Rob Romijnders, Stefanos Laskaridis, Ali Shahin Shamsabadi, Hamed Haddadi
2025	J	`jnl`	Privacy Practices of Browser Agents. CoRR Alisha Ukani, Hamed Haddadi, Ali Shahin Shamsabadi, Peter Snyder
2024	A*	`conf`	Confidential-DPproof: Confidential Proof of Differentially Private Training. ICLR Ali Shahin Shamsabadi, Gefei Tan, Tudor Cebere, Aurélien Bellet, Hamed Haddadi, Nicolas Papernot, Xiao Wang, Adrian Weller
2024	J	`jnl`	Context-Aware Membership Inference Attacks against Pre-trained Large Language Models. CoRR Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Reza Shokri
2024	J	`jnl`	Nebula: Efficient, Private and Accurate Histogram Estimation. CoRR Ali Shahin Shamsabadi, Peter Snyder, Ralph Giles, Aurélien Bellet, Hamed Haddadi
2024	J	`jnl`	OATH: Efficient and Flexible Zero-Knowledge Proofs of End-to-End ML Fairness. CoRR Olive Franzese, Ali Shahin Shamsabadi, Hamed Haddadi
2023	A*	`conf`	Confidential-PROFITT: Confidential PROof of FaIr Training of Trees. ICLR Ali Shahin Shamsabadi, Sierra Calanda Wyllie, Nicholas Franzese, Natalie Dullerud, Sébastien Gambs, Nicolas Papernot, Xiao Wang, Adrian Weller
2023	J	`jnl`	Differentially Private Speaker Anonymization. Proc. Priv. Enhancing Technol. Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet, Nathalie Vauquier, Emmanuel Vincent, Mohamed Maouche, Marc Tommasi, Nicolas Papernot
2023	A*	`conf`	GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation. USENIX Security Symposium Sina Sajadmanesh, Ali Shahin Shamsabadi, Aurélien Bellet, Daniel Gatica-Perez
2023	J	`jnl`	Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey. CoRR Victoria Smith, Ali Shahin Shamsabadi, Carolyn Ashurst, Adrian Weller
2023	J	`jnl`	Is Federated Learning a Practical PET Yet? CoRR Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2023	J	`jnl`	Losing Less: A Loss for Differentially Private Deep Learning. Proc. Priv. Enhancing Technol. Ali Shahin Shamsabadi, Nicolas Papernot
2023	A	`conf`	Mnemonist: Locating Model Parameters that Memorize Training Examples. UAI Ali Shahin Shamsabadi, Jamie Hayes, Borja Balle, Adrian Weller
2023	J	`jnl`	Private Multi-Winner Voting for Machine Learning. Proc. Priv. Enhancing Technol. Adam Dziedzic, Christopher A. Choquette-Choo, Natalie Dullerud, Vinith M. Suriyakumar, Ali Shahin Shamsabadi, Muhammad Ahmad Kaleem, Somesh Jha, Nicolas Papernot, Xiao Wang
2023	A	`conf`	Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation. EuroS&P Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2023	A*	`conf`	Tubes Among Us: Analog Attack on Automatic Speaker Identification. USENIX Security Symposium Shimaa Ahmed, Yash Wani, Ali Shahin Shamsabadi, Mohammad Yaghini, Ilia Shumailov, Nicolas Papernot, Kassem Fawaz
2023	A	`conf`	When the Curious Abandon Honesty: Federated Learning Is Not Private. EuroS&P Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2022	A*	`conf`	A Zest of LIME: Towards Architecture-Independent Model Distances. ICLR Hengrui Jia, Hongyu Chen, Jonas Guan, Ali Shahin Shamsabadi, Nicolas Papernot
2022	J	`jnl`	Differentially Private Speaker Anonymization. CoRR Ali Shahin Shamsabadi, Brij Mohan Lal Srivastava, Aurélien Bellet, Nathalie Vauquier, Emmanuel Vincent, Mohamed Maouche, Marc Tommasi, Nicolas Papernot
2022	J	`jnl`	GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation. CoRR Sina Sajadmanesh, Ali Shahin Shamsabadi, Aurélien Bellet, Daniel Gatica-Perez
2022	J	`jnl`	On the reversibility of adversarial attacks. CoRR Chau Yi Li, Ricardo Sánchez-Matilla, Ali Shahin Shamsabadi, Riccardo Mazzon, Andrea Cavallaro
2022	J	`jnl`	Pipe Overflow: Smashing Voice Authentication for Fun and Profit. CoRR Shimaa Ahmed, Yash Wani, Ali Shahin Shamsabadi, Mohammad Yaghini, Ilia Shumailov, Nicolas Papernot, Kassem Fawaz
2022	J	`jnl`	Private Multi-Winner Voting for Machine Learning. CoRR Adam Dziedzic, Christopher A. Choquette-Choo, Natalie Dullerud, Vinith Menon Suriyakumar, Ali Shahin Shamsabadi, Muhammad Ahmad Kaleem, Somesh Jha, Nicolas Papernot, Xiao Wang
2022	A*	`conf`	Washing The Unwashable : On The (Im)possibility of Fairwashing Detection. NeurIPS Ali Shahin Shamsabadi, Mohammad Yaghini, Natalie Dullerud, Sierra Calanda Wyllie, Ulrich Aïvodji, Aisha Alaagib, Sébastien Gambs, Nicolas Papernot
2021	Misc	`conf`	FoolHD: Fooling Speaker Identification by Highly Imperceptible Adversarial Disturbances. ICASSP Ali Shahin Shamsabadi, Francisco Sepúlveda Teixeira, Alberto Abad, Bhiksha Raj, Andrea Cavallaro, Isabel Trancoso
2021	B	`conf`	On the Reversibility of Adversarial Attacks. ICIP Chau Yi Li, Ricardo Sánchez-Matilla, Ali Shahin Shamsabadi, Riccardo Mazzon, Andrea Cavallaro
2021	J	`jnl`	Semantically Adversarial Learnable Filters. IEEE Trans. Image Process. Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro
2021	J	`jnl`	When the Curious Abandon Honesty: Federated Learning Is Not Private. CoRR Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot
2020	J	`jnl`	A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics. IEEE Internet Things J. Seyed Ali Osia, Ali Shahin Shamsabadi, Sina Sajadmanesh, Ali Taheri, Kleomenis Katevas, Hamid R. Rabiee, Nicholas D. Lane, Hamed Haddadi
2020	A*	`conf`	ColorFool: Semantic Adversarial Colorization. CVPR Ali Shahin Shamsabadi, Ricardo Sánchez-Matilla, Andrea Cavallaro
2020	J	`jnl`	DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments. CoRR Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, Hamed Haddadi
2020	A	`conf`	DarkneTZ: towards model privacy at the edge using trusted execution environments. MobiSys Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, Hamed Haddadi
2020	A*	`conf`	Deep Learning for Privacy in Multimedia. ACM Multimedia Andrea Cavallaro, Mohammad Malekzadeh, Ali Shahin Shamsabadi
2020	J	`jnl`	Deep Private-Feature Extraction. IEEE Trans. Knowl. Data Eng. Seyed Ali Osia, Ali Taheri, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Hamid R. Rabiee
2020	Misc	`conf`	Edgefool: an Adversarial Image Enhancement Filter. ICASSP Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro
2020	J	`jnl`	Exploiting Vulnerabilities of Deep Neural Networks for Privacy Protection. IEEE Trans. Multim. Ricardo Sanchez-Matilla, Chau Yi Li, Ali Shahin Shamsabadi, Riccardo Mazzon, Andrea Cavallaro
2020	J	`jnl`	Exploiting vulnerabilities of deep neural networks for privacy protection. CoRR Ricardo Sanchez-Matilla, Chau Yi Li, Ali Shahin Shamsabadi, Riccardo Mazzon, Andrea Cavallaro
2020	J	`jnl`	FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances. CoRR Ali Shahin Shamsabadi, Francisco Sepúlveda Teixeira, Alberto Abad, Bhiksha Raj, Andrea Cavallaro, Isabel Trancoso
2020	J	`jnl`	PrivEdge: From Local to Distributed Private Training and Prediction. CoRR Ali Shahin Shamsabadi, Adrià Gascón, Hamed Haddadi, Andrea Cavallaro
2020	J	`jnl`	PrivEdge: From Local to Distributed Private Training and Prediction. IEEE Trans. Inf. Forensics Secur. Ali Shahin Shamsabadi, Adrià Gascón, Hamed Haddadi, Andrea Cavallaro
2020	J	`jnl`	Semantically Adversarial Learnable Filters. CoRR Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro
2019	J	`jnl`	ColorFool: Semantic Adversarial Colorization. CoRR Ali Shahin Shamsabadi, Ricardo Sanchez-Matilla, Andrea Cavallaro
2019	J	`jnl`	EdgeFool: An Adversarial Image Enhancement Filter. CoRR Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro
2019	A*	`conf`	Poster: Towards Characterizing and Limiting Information Exposure in DNN Layers. CCS Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Andrea Cavallaro, Hamed Haddadi
2019	A*	`conf`	QUOTIENT: Two-Party Secure Neural Network Training and Prediction. CCS Nitin Agrawal, Ali Shahin Shamsabadi, Matt J. Kusner, Adrià Gascón
2019	J	`jnl`	QUOTIENT: Two-Party Secure Neural Network Training and Prediction. CoRR Nitin Agrawal, Ali Shahin Shamsabadi, Matt J. Kusner, Adrià Gascón
2019	Misc	`conf`	Scene Privacy Protection. ICASSP Chau Yi Li, Ali Shahin Shamsabadi, Ricardo Sanchez-Matilla, Riccardo Mazzon, Andrea Cavallaro
2019	J	`jnl`	Towards Characterizing and Limiting Information Exposure in DNN Layers. CoRR Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Andrea Cavallaro, Hamed Haddadi
2018	J	`jnl`	Deep Private-Feature Extraction. CoRR Seyed Ali Ossia, Ali Taheri, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Hamid R. Rabiee
2018	B	`conf`	Distributed One-Class Learning. ICIP Ali Shahin Shamsabadi, Hamed Haddadi, Andrea Cavallaro
2018	J	`jnl`	Distributed One-class Learning. CoRR Ali Shahin Shamsabadi, Hamed Haddadi, Andrea Cavallaro
2018	J	`jnl`	Private and Scalable Personal Data Analytics Using Hybrid Edge-to-Cloud Deep Learning. Computer Seyed Ali Ossia, Ali Shahin Shamsabadi, Ali Taheri, Hamid R. Rabiee, Hamed Haddadi
2018	—	`conf`	Providing Occupancy as a Service with Databox. CitiFog@SenSys Poonam Yadav, John Moore, Qi Li, Richard Mortier, Anthony Brown, Andy Crabtree, Chris Greenhalgh, Derek McAuley, Yousef Amar, Ali Shahin Shamsabadi, Hamed Haddadi
2017	J	`jnl`	A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics. CoRR Seyed Ali Ossia, Ali Shahin Shamsabadi, Ali Taheri, Hamid R. Rabiee, Nicholas D. Lane, Hamed Haddadi
2017	—	`conf`	A new algorithm for training sparse autoencoders. EUSIPCO Ali Shahin Shamsabadi, Massoud Babaie-Zadeh, Seyyede Zohreh Seyyedsalehi, Hamid R. Rabiee, Christian Jutten
2017	J	`jnl`	Privacy-Preserving Deep Inference for Rich User Data on The Cloud. CoRR Seyed Ali Ossia, Ali Shahin Shamsabadi, Ali Taheri, Kleomenis Katevas, Hamid R. Rabiee, Nicholas D. Lane, Hamed Haddadi