Eugene Bagdasaryan

27 papers A* 5A 3Journal 18Unranked 1

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	Adversarial Illusions in Multi-Modal Embeddings. USENIX Security Symposium Tingwei Zhang, Rishi D. Jha, Eugene Bagdasaryan, Vitaly Shmatikov
2024	J	`jnl`	Air Gap: Protecting Privacy-Conscious Conversational Agents. CoRR Eugene Bagdasaryan, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage
2024	J	`jnl`	Injecting Bias in Text-To-Image Models via Composite-Trigger Backdoors. CoRR Ali Naseh, Jaechul Roh, Eugene Bagdasaryan, Amir Houmansadr
2024	J	`jnl`	Operationalizing Contextual Integrity in Privacy-Conscious Assistants. CoRR 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
2024	J	`jnl`	Soft Prompts Go Hard: Steering Visual Language Models with Hidden Meta-Instructions. CoRR Tingwei Zhang, Collin Zhang, John X. Morris, Eugene Bagdasaryan, Vitaly Shmatikov
2024	J	`jnl`	UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI. CoRR Ilia Shumailov, Jamie Hayes, Eleni Triantafillou, Guillermo Ortiz-Jiménez, Nicolas Papernot, Matthew Jagielski, Itay Yona, Heidi Howard, Eugene Bagdasaryan
2023	J	`jnl`	(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs. CoRR Eugene Bagdasaryan, Tsung-Yin Hsieh, Ben Nassi, Vitaly Shmatikov
2023	J	`jnl`	Ceci n'est pas une pomme: Adversarial Illusions in Multi-Modal Embeddings. CoRR Eugene Bagdasaryan, Vitaly Shmatikov
2023	J	`jnl`	Hyperparameter Search Is All You Need For Training-Agnostic Backdoor Robustness. CoRR Eugene Bagdasaryan, Vitaly Shmatikov
2023	J	`jnl`	Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models. CoRR Sze Jue Yang, Chinh D. La, Quang H. Nguyen, Eugene Bagdasaryan, Kok-Seng Wong, Anh Tuan Tran, Chee Seng Chan, Khoa D. Doan
2022	A*	`conf`	Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures. SP Eugene Bagdasaryan, Vitaly Shmatikov
2022	J	`jnl`	Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation. Proc. Priv. Enhancing Technol. Eugene Bagdasaryan, Peter Kairouz, Stefan Mellem, Adrià Gascón, Kallista A. Bonawitz, Deborah Estrin, Marco Gruteser
2022	J	`jnl`	Training a Tokenizer for Free with Private Federated Learning. CoRR Eugene Bagdasaryan, Congzheng Song, Rogier C. van Dalen, Matt Seigel, Áine Cahill
2021	A*	`conf`	Blind Backdoors in Deep Learning Models. USENIX Security Symposium Eugene Bagdasaryan, Vitaly Shmatikov
2021	J	`jnl`	Spinning Language Models for Propaganda-As-A-Service. CoRR Eugene Bagdasaryan, Vitaly Shmatikov
2021	J	`jnl`	Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation. CoRR Eugene Bagdasaryan, Peter Kairouz, Stefan Mellem, Adrià Gascón, Kallista A. Bonawitz, Deborah Estrin, Marco Gruteser
2020	J	`jnl`	Blind Backdoors in Deep Learning Models. CoRR Eugene Bagdasaryan, Vitaly Shmatikov
2020	J	`jnl`	Decentralized Policy-Based Private Analytics. CoRR Kleomenis Katevas, Eugene Bagdasaryan, Jason Waterman, Mohamad Mounir Safadieh, Hamed Haddadi, Deborah Estrin
2020	A	`conf`	How To Backdoor Federated Learning. AISTATS Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov
2020	J	`jnl`	Salvaging Federated Learning by Local Adaptation. CoRR Tao Yu, Eugene Bagdasaryan, Vitaly Shmatikov
2019	—	`conf`	Ancile: Enhancing Privacy for Ubiquitous Computing with Use-Based Privacy. WPES@CCS Eugene Bagdasaryan, Griffin Berlstein, Jason Waterman, Eleanor Birrell, Nate Foster, Fred B. Schneider, Deborah Estrin
2019	A*	`conf`	Differential Privacy Has Disparate Impact on Model Accuracy. NeurIPS Eugene Bagdasaryan, Omid Poursaeed, Vitaly Shmatikov
2019	J	`jnl`	Differential Privacy Has Disparate Impact on Model Accuracy. CoRR Eugene Bagdasaryan, Vitaly Shmatikov
2019	A*	`conf`	X-Containers: Breaking Down Barriers to Improve Performance and Isolation of Cloud-Native Containers. ASPLOS Zhiming Shen, Zhen Sun, Gur-Eyal Sela, Eugene Bagdasaryan, Christina Delimitrou, Robbert van Renesse, Hakim Weatherspoon
2018	J	`jnl`	How To Backdoor Federated Learning. CoRR Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov
2018	A	`conf`	Modularizing deep neural network-inspired recommendation algorithms. RecSys Longqi Yang, Eugene Bagdasaryan, Hongyi Wen
2018	A	`conf`	OpenRec: A Modular Framework for Extensible and Adaptable Recommendation Algorithms. WSDM Longqi Yang, Eugene Bagdasaryan, Joshua Gruenstein, Cheng-Kang Hsieh, Deborah Estrin