Fatemehsadat Mireshghallah

43 papers A* 6B 2Journal 27Unranked 8

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation. ICLR Xinyu Tang, Richard Shin, Huseyin A. Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Robert Sim
2023	B	`conf`	A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation. CoNLL Jarad Forristal, Fatemehsadat Mireshghallah, Greg Durrett, Taylor Berg-Kirkpatrick
2023	J	`jnl`	Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization. CoRR Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu, Fatemehsadat Mireshghallah
2023	J	`jnl`	LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud. CoRR Mengke Zhang, Tianxing He, Tianle Wang, Lu Mi, Fatemehsadat Mireshghallah, Binyi Chen, Hao Wang, Yulia Tsvetkov
2023	—	`conf`	Membership Inference Attacks against Language Models via Neighbourhood Comparison. ACL (Findings) Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
2023	J	`jnl`	Membership Inference Attacks against Language Models via Neighbourhood Comparison. CoRR Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
2023	—	`conf`	Privacy-Preserving Domain Adaptation of Semantic Parsers. ACL (1) Fatemehsadat Mireshghallah, Yu Su, Tatsunori Hashimoto, Jason Eisner, Richard Shin
2023	J	`jnl`	Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation. CoRR Xinyu Tang, Richard Shin, Huseyin A. Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Robert Sim
2023	J	`jnl`	Smaller Language Models are Better Black-box Machine-Generated Text Detectors. CoRR Fatemehsadat Mireshghallah, Justus Mattern, Sicun Gao, Reza Shokri, Taylor Berg-Kirkpatrick
2022	A*	`conf`	An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models. EMNLP Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David E. Evans, Taylor Berg-Kirkpatrick
2022	A*	`conf`	Differentially Private Model Compression. NeurIPS Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A. Inan, Lukas Wutschitz, Janardhan Kulkarni
2022	J	`jnl`	Differentially Private Model Compression. CoRR Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A. Inan, Lukas Wutschitz, Janardhan Kulkarni
2022	J	`jnl`	Memorization in NLP Fine-tuning Methods. CoRR Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, Taylor Berg-Kirkpatrick
2022	J	`jnl`	Mix and Match: Learning-free Controllable Text Generation using Energy Language Models. CoRR Fatemehsadat Mireshghallah, Kartik Goyal, Taylor Berg-Kirkpatrick
2022	—	`conf`	Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models. ACL (1) Fatemehsadat Mireshghallah, Kartik Goyal, Taylor Berg-Kirkpatrick
2022	J	`jnl`	Non-Parametric Temporal Adaptation for Social Media Topic Classification. CoRR Fatemehsadat Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick
2022	J	`jnl`	Privacy-Preserving Domain Adaptation of Semantic Parsers. CoRR Fatemehsadat Mireshghallah, Richard Shin, Yu Su, Tatsunori Hashimoto, Jason Eisner
2022	A*	`conf`	Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. EMNLP Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri
2022	J	`jnl`	Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. CoRR Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri
2022	—	`conf`	UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis. NAACL-HLT Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
2022	—	`conf`	What Does it Mean for a Language Model to Preserve Privacy? FAccT Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, Florian Tramèr
2022	J	`jnl`	What Does it Mean for a Language Model to Preserve Privacy? CoRR Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, Florian Tramèr
2021	J	`jnl`	Benchmarking Differential Privacy and Federated Learning for BERT Models. CoRR Priyam Basu, Tiasa Singha Roy, Rakshit Naidu, Zümrüt Müftüoglu, Sahib Singh, Fatemehsadat Mireshghallah
2021	J	`jnl`	DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy? CoRR Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh, Patrik Joslin Kenfack, Fatemehsadat Mireshghallah, Andrew Trask
2021	J	`jnl`	Efficient Hyperparameter Optimization for Differentially Private Deep Learning. CoRR Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah, Mohammad Malekzadeh
2021	A*	`conf`	Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy. WWW Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali, Ahmed Taha Elthakeb, Dean M. Tullsen, Hadi Esmaeilzadeh
2021	J	`jnl`	Privacy Regularization: Joint Privacy-Utility Optimization in Language Models. CoRR Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim
2021	—	`conf`	Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels. NAACL-HLT Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim
2021	—	`conf`	Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness. EMNLP (1) Fatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick
2021	J	`jnl`	Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness. CoRR Fatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick
2021	B	`conf`	U-Noise: Learnable Noise Masks for Interpretable Image Segmentation. ICIP Teddy Koker, Fatemehsadat Mireshghallah, Tom Titcombe, Georgios Kaissis
2021	J	`jnl`	U-Noise: Learnable Noise Masks for Interpretable Image Segmentation. CoRR Teddy Koker, Fatemehsadat Mireshghallah, Tom Titcombe, Georgios Kaissis
2021	J	`jnl`	UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis. CoRR Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
2021	J	`jnl`	When Differential Privacy Meets Interpretability: A Case Study. CoRR Rakshit Naidu, Aman Priyanshu, Aadith Kumar, Sasikanth Kotti, Haofan Wang, Fatemehsadat Mireshghallah
2020	J	`jnl`	A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference. CoRR Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali, Ahmed Taha Elthakeb, Dean M. Tullsen, Hadi Esmaeilzadeh
2020	J	`jnl`	Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization. CoRR Ahmed T. Elthakeb, Prannoy Pilligundla, Fatemehsadat Mireshghallah, Tarek Elgindi, Charles-Alban Deledalle, Hadi Esmaeilzadeh
2020	—	`conf`	Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy. PPMLP@CCS Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh, Andrew Trask
2020	J	`jnl`	Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy. CoRR Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh, Andrew Trask
2020	J	`jnl`	Privacy in Deep Learning: A Survey. CoRR Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh
2020	J	`jnl`	ReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks. IEEE Micro Ahmed T. Elthakeb, Prannoy Pilligundla, Fatemehsadat Mireshghallah, Amir Yazdanbakhsh, Hadi Esmaeilzadeh
2020	A*	`conf`	Shredder: Learning Noise Distributions to Protect Inference Privacy. ASPLOS Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Ali Jalali, Dean M. Tullsen, Hadi Esmaeilzadeh
2019	J	`jnl`	Energy-Efficient Permanent Fault Tolerance in Hard Real-Time Systems. IEEE Trans. Computers Fatemehsadat Mireshghallah, Mohammad Bakhshalipour, Mohammad Sadrosadati, Hamid Sarbazi-Azad
2019	J	`jnl`	Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge. CoRR Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Dean M. Tullsen, Hadi Esmaeilzadeh