Milad Nasr

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 57

Top Topics

Machine Learning

Diffusion Models

Top Venues

USENIX Security Symposium

IEEE Symposium on Security and Privacy

Publications

Harsh Chaudhari, Giorgio Severi, John Abascal, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation. CoRR (2024)
Aldo G. Carranza, Rezsa Farahani, Natalia Ponomareva, Alexey Kurakin, Matthew Jagielski, Milad Nasr
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models. NAACL-HLT (2024)
Jonathan Hayase, Ema Borevkovic, Nicholas Carlini, Florian Tramèr, Milad Nasr
Query-Based Adversarial Prompt Generation. CoRR (2024)
Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, Prateek Mittal
Private Fine-tuning of Large Language Models with Zeroth-order Optimization. CoRR (2024)
Nicholas Carlini, Daniel Paleka, Krishnamurthy (Dj) Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr
Stealing Part of a Production Language Model. CoRR (2024)
Edoardo Debenedetti, Giorgio Severi, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Eric Wallace, Nicholas Carlini, Florian Tramèr
Privacy Side Channels in Machine Learning Systems. USENIX Security Symposium (2024)
Karan Chadha, Matthew Jagielski, Nicolas Papernot, Christopher A. Choquette-Choo, Milad Nasr
Auditing Private Prediction. CoRR (2024)
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang
Why Is Public Pretraining Necessary for Private Model Training? ICML (2023)
Thomas Steinke, Milad Nasr, Matthew Jagielski
Privacy Auditing with One (1) Training Run. CoRR (2023)
Daphne Ippolito, Nicholas Carlini, Katherine Lee, Milad Nasr, Yun William Yu
Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System. CoRR (2023)
Matthew Jagielski, Milad Nasr, Christopher A. Choquette-Choo, Katherine Lee, Nicholas Carlini
Students Parrot Their Teachers: Membership Inference on Model Distillation. CoRR (2023)
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
Why Is Public Pretraining Necessary for Private Model Training? CoRR (2023)
Matthew Jagielski, Milad Nasr, Katherine Lee, Christopher A. Choquette-Choo, Nicholas Carlini, Florian Tramèr
Students Parrot Their Teachers: Membership Inference on Model Distillation. NeurIPS (2023)
Milad Nasr, Saeed Mahloujifar, Xinyu Tang, Prateek Mittal, Amir Houmansadr
Effectively Using Public Data in Privacy Preserving Machine Learning. ICML (2023)
Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace
Extracting Training Data from Diffusion Models. USENIX Security Symposium (2023)
Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Eric Wallace, Florian Tramèr, Katherine Lee
Scalable Extraction of Training Data from (Production) Language Models. CoRR (2023)
Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
Tight Auditing of Differentially Private Machine Learning. CoRR (2023)
Daphne Ippolito, Florian Tramèr, Milad Nasr, Chiyuan Zhang, Matthew Jagielski, Katherine Lee, Christopher A. Choquette-Choo, Nicholas Carlini
Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy. INLG (2023)
Aldo Gael Carranza, Rezsa Farahani, Natalia Ponomareva, Alex Kurakin, Matthew Jagielski, Milad Nasr
Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models. CoRR (2023)
Thomas Steinke, Milad Nasr, Matthew Jagielski
Privacy Auditing with One (1) Training Run. NeurIPS (2023)
Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace
Extracting Training Data from Diffusion Models. CoRR (2023)
Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Anas Awadalla, Pang Wei Koh, Daphne Ippolito, Katherine Lee, Florian Tramèr, Ludwig Schmidt
Are aligned neural networks adversarially aligned? CoRR (2023)
Milad Nasr, Jamie Hayes, Thomas Steinke, Borja Balle, Florian Tramèr, Matthew Jagielski, Nicholas Carlini, Andreas Terzis
Tight Auditing of Differentially Private Machine Learning. USENIX Security Symposium (2023)
Meisam Hejazinia, Dzmitry Huba, Ilias Leontiadis, Kiwan Maeng, Mani Malek, Luca Melis, Ilya Mironov, Milad Nasr, Kaikai Wang, Carole-Jean Wu
Federated Ensemble Learning: Increasing the Capacity of Label Private Recommendation Systems. IEEE Data Eng. Bull. 46 (1) (2023)
Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei Koh, Daphne Ippolito, Florian Tramèr, Ludwig Schmidt
Are aligned neural networks adversarially aligned? NeurIPS (2023)
A. Feder Cooper, Katherine Lee, James Grimmelmann, Daphne Ippolito, Christopher Callison-Burch, Christopher A. Choquette-Choo, Niloofar Mireshghallah, Miles Brundage, David Mimno, Madiha Zahrah Choksi, Jack M. Balkin, Nicholas Carlini, Christopher De Sa, Jonathan Frankle, Deep Ganguli, Bryant Gipson, Andres Guadamuz, Swee Leng Harris, Abigail Z. Jacobs, Elizabeth Joh, Gautam Kamath, Mark Lemley, Cass Matthews, Christine McLeavey, Corynne McSherry, Milad Nasr, Paul Ohm, Adam Roberts, Tom Rubin, Pamela Samuelson, Ludwig Schubert, Kristen Vaccaro, Luis Villa, Felix Wu, Elana Zeide
Report of the 1st Workshop on Generative AI and Law. CoRR (2023)
Edoardo Debenedetti, Giorgio Severi, Nicholas Carlini, Christopher A. Choquette-Choo, Matthew Jagielski, Milad Nasr, Eric Wallace, Florian Tramèr
Privacy Side Channels in Machine Learning Systems. CoRR (2023)
Daphne Ippolito, Nicholas Carlini, Katherine Lee, Milad Nasr, Yun William Yu
Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System. INLG (2023)
Xinyu Tang, Milad Nasr, Saeed Mahloujifar, Virat Shejwalkar, Liwei Song, Amir Houmansadr, Prateek Mittal
Machine Learning with Differentially Private Labels: Mechanisms and Frameworks. Proc. Priv. Enhancing Technol. 2022 (4) (2022)
Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, Florian Tramèr
Membership Inference Attacks From First Principles. IEEE Symposium on Security and Privacy (2022)
Meisam Hejazinia, Dzmitry Huba, Ilias Leontiadis, Kiwan Maeng, Mani Malek, Luca Melis, Ilya Mironov, Milad Nasr, Kaikai Wang, Carole-Jean Wu
FEL: High Capacity Learning for Recommendation and Ranking via Federated Ensemble Learning. CoRR (2022)
Nicholas Carlini, Vitaly Feldman, Milad Nasr
No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy". CoRR (2022)
Xinyu Tang, Saeed Mahloujifar, Liwei Song, Virat Shejwalkar, Milad Nasr, Amir Houmansadr, Prateek Mittal
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture. USENIX Security Symposium (2022)
Daphne Ippolito, Florian Tramèr, Milad Nasr, Chiyuan Zhang, Matthew Jagielski, Katherine Lee, Christopher A. Choquette-Choo, Nicholas Carlini
Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy. CoRR (2022)
Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. IEEE Symposium on Security and Privacy (2021)
Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, Florian Tramèr
Membership Inference Attacks From First Principles. CoRR (2021)
Milad Nasr, Alireza Bahramali, Amir Houmansadr
Defeating DNN-Based Traffic Analysis Systems in Real-Time With Blind Adversarial Perturbations. USENIX Security Symposium (2021)
Alireza Bahramali, Milad Nasr, Amir Houmansadr, Dennis Goeckel, Don Towsley
Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems. CCS (2021)
Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. CoRR (2021)
Alireza Bahramali, Milad Nasr, Amir Houmansadr, Dennis Goeckel, Don Towsley
Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems. CoRR (2021)
Xinyu Tang, Saeed Mahloujifar, Liwei Song, Virat Shejwalkar, Milad Nasr, Amir Houmansadr, Prateek Mittal
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture. CoRR (2021)
Milad Nasr, Reza Shokri, Amir Houmansadr
Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising. CoRR (2020)
Milad Nasr, Alireza Bahramali, Amir Houmansadr
Blind Adversarial Network Perturbations. CoRR (2020)
Milad Nasr, Michael Carl Tschantz
Bidding strategies with gender nondiscrimination constraints for online ad auctions. FAT* (2020)
Milad Nasr, Hadi Zolfaghari, Amir Houmansadr, Amirhossein Ghafari
MassBrowser: Unblocking the Censored Web for the Masses, by the Masses. NDSS (2020)
Milad Nasr, Reza Shokri, Amir Houmansadr
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning. IEEE Symposium on Security and Privacy (2019)
Milad Nasr, Sadegh Farhang, Amir Houmansadr, Jens Grossklags
Enemy At the Gateways: Censorship-Resilient Proxy Distribution Using Game Theory. NDSS (2019)
Milad Nasr, Michael Carl Tschantz
Bidding Strategies with Gender Nondiscrimination: Constraints for Online Ad Auctions. CoRR (2019)
Milad Nasr, Alireza Bahramali, Amir Houmansadr
DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning. CoRR (2018)
Milad Nasr, Reza Shokri, Amir Houmansadr
Machine Learning with Membership Privacy using Adversarial Regularization. CCS (2018)
Milad Nasr, Reza Shokri, Amir Houmansadr
Machine Learning with Membership Privacy using Adversarial Regularization. CoRR (2018)
Milad Nasr, Alireza Bahramali, Amir Houmansadr
DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning. CCS (2018)
Milad Nasr, Reza Shokri, Amir Houmansadr
Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks. CoRR (2018)
Milad Nasr, Amir Houmansadr, Arya Mazumdar
Compressive Traffic Analysis: A New Paradigm for Scalable Traffic Analysis. CCS (2017)
Milad Nasr, Sadegh Farhang, Amir Houmansadr, Jens Grossklags
Enemy At the Gateways: A Game Theoretic Approach to Proxy Distribution. CoRR (2017)
Milad Nasr, Hadi Zolfaghari, Amir Houmansadr
The Waterfall of Liberty: Decoy Routing Circumvention that Resists Routing Attacks. CCS (2017)
Milad Nasr, Amir Houmansadr
GAME OF DECOYS: Optimal Decoy Routing Through Game Theory. CCS (2016)