Eugene Bagdasarian

According to our database, Eugene Bagdasarian authored at least 25 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of four.

2024

CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data.

Zhao Cheng, Diane Wan, Matthew Abueg, Sahra Ghalebikesabi, Ren Yi, Eugene Bagdasarian, Borja Balle, Stefan Mellem, Shawn O'Banion

CoRR, 2024

Operationalizing Contextual Integrity in Privacy-Conscious Assistants.

Sahra Ghalebikesabi, Eugene Bagdasaryan, Ren Yi, Itay Yona, Ilia Shumailov, Aneesh Pappu, Chongyang Shi, Laura Weidinger, Robert Stanforth, Leonard Berrada, Pushmeet Kohli, Po-Sen Huang, Borja Balle

CoRR, 2024

Soft Prompts Go Hard: Steering Visual Language Models with Hidden Meta-Instructions.

Tingwei Zhang, Collin Zhang, John X. Morris, Eugene Bagdasaryan, Vitaly Shmatikov

CoRR, 2024

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI.

Ilia Shumailov, Jamie Hayes, Eleni Triantafillou, Guillermo Ortiz-Jiménez, Nicolas Papernot, Matthew Jagielski, Itay Yona, Heidi Howard, Eugene Bagdasaryan

CoRR, 2024

Injecting Bias in Text-To-Image Models via Composite-Trigger Backdoors.

Ali Naseh, Jaechul Roh, Eugene Bagdasaryan, Amir Houmansadr

CoRR, 2024

Air Gap: Protecting Privacy-Conscious Conversational Agents.

Eugene Bagdasaryan, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage

CoRR, 2024

Adversarial Illusions in Multi-Modal Embeddings.

Tingwei Zhang, Rishi D. Jha, Eugene Bagdasaryan, Vitaly Shmatikov

Proceedings of the 33rd USENIX Security Symposium, 2024

2023

Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models.

Sze Jue Yang, Chinh D. La, Quang H. Nguyen, Eugene Bagdasaryan, Kok-Seng Wong, Anh Tuan Tran, Chee Seng Chan, Khoa D. Doan

CoRR, 2023

Ceci n'est pas une pomme: Adversarial Illusions in Multi-Modal Embeddings.

Eugene Bagdasaryan, Vitaly Shmatikov

CoRR, 2023

(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs.

Eugene Bagdasaryan, Tsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov

CoRR, 2023

Hyperparameter Search Is All You Need For Training-Agnostic Backdoor Robustness.

Eugene Bagdasaryan, Vitaly Shmatikov

CoRR, 2023

2022

Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation.

Eugene Bagdasaryan, Peter Kairouz, Stefan Mellem, Adrià Gascón, Kallista A. Bonawitz, Deborah Estrin, Marco Gruteser

Proc. Priv. Enhancing Technol., 2022

Training a Tokenizer for Free with Private Federated Learning.

Eugene Bagdasaryan, Congzheng Song, Rogier C. van Dalen, Matt Seigel, Áine Cahill

CoRR, 2022

Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures.

Eugene Bagdasaryan, Vitaly Shmatikov

Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022

2021

Spinning Language Models for Propaganda-As-A-Service.

Eugene Bagdasaryan, Vitaly Shmatikov

CoRR, 2021

Blind Backdoors in Deep Learning Models.

Eugene Bagdasaryan, Vitaly Shmatikov

Proceedings of the 30th USENIX Security Symposium, 2021

2020

Decentralized Policy-Based Private Analytics.

Kleomenis Katevas, Eugene Bagdasaryan, Jason Waterman, Mohamad Mounir Safadieh, Hamed Haddadi, Deborah Estrin

CoRR, 2020

Salvaging Federated Learning by Local Adaptation.

Tao Yu, Eugene Bagdasaryan, Vitaly Shmatikov

CoRR, 2020

How To Backdoor Federated Learning.

Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Differential Privacy Has Disparate Impact on Model Accuracy.

Eugene Bagdasaryan, Vitaly Shmatikov

CoRR, 2019

Ancile: Enhancing Privacy for Ubiquitous Computing with Use-Based Privacy.

Eugene Bagdasaryan, Griffin Berlstein, Jason Waterman, Eleanor Birrell, Nate Foster, Fred B. Schneider, Deborah Estrin

Proceedings of the 18th ACM Workshop on Privacy in the Electronic Society, 2019

Differential Privacy Has Disparate Impact on Model Accuracy.

Eugene Bagdasaryan, Omid Poursaeed, Vitaly Shmatikov

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

X-Containers: Breaking Down Barriers to Improve Performance and Isolation of Cloud-Native Containers.

Zhiming Shen, Zhen Sun, Gur-Eyal Sela, Eugene Bagdasaryan, Christina Delimitrou, Robbert van Renesse, Hakim Weatherspoon

Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, 2019

2018

OpenRec: A Modular Framework for Extensible and Adaptable Recommendation Algorithms.

Longqi Yang, Eugene Bagdasaryan, Joshua Gruenstein, Cheng-Kang Hsieh, Deborah Estrin

Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, 2018

Modularizing deep neural network-inspired recommendation algorithms.

Longqi Yang, Eugene Bagdasaryan, Hongyi Wen

Proceedings of the 12th ACM Conference on Recommender Systems, 2018