Fatemehsadat Mireshghallah

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 43

Top Topics

Text Generation

Differential Privacy

Top Venues

Publications

Xinyu Tang, Richard Shin, Huseyin A. Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Robert Sim
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation. ICLR (2024)
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
Membership Inference Attacks against Language Models via Neighbourhood Comparison. ACL (Findings) (2023)
Fatemehsadat Mireshghallah, Justus Mattern, Sicun Gao, Reza Shokri, Taylor Berg-Kirkpatrick
Smaller Language Models are Better Black-box Machine-Generated Text Detectors. CoRR (2023)
Fatemehsadat Mireshghallah, Yu Su, Tatsunori Hashimoto, Jason Eisner, Richard Shin
Privacy-Preserving Domain Adaptation of Semantic Parsers. ACL (1) (2023)
Xinyu Tang, Richard Shin, Huseyin A. Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, Robert Sim
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation. CoRR (2023)
Jarad Forristal, Fatemehsadat Mireshghallah, Greg Durrett, Taylor Berg-Kirkpatrick
A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation. CoNLL (2023)
Mengke Zhang, Tianxing He, Tianle Wang, Lu Mi, Fatemehsadat Mireshghallah, Binyi Chen, Hao Wang, Yulia Tsvetkov
LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud. CoRR (2023)
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
Membership Inference Attacks against Language Models via Neighbourhood Comparison. CoRR (2023)
Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu, Fatemehsadat Mireshghallah
Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization. CoRR (2023)
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis. NAACL-HLT (2022)
Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, Florian Tramèr
What Does it Mean for a Language Model to Preserve Privacy? FAccT (2022)
Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. EMNLP (2022)
Fatemehsadat Mireshghallah, Kartik Goyal, Taylor Berg-Kirkpatrick
Mix and Match: Learning-free Controllable Text Generation using Energy Language Models. CoRR (2022)
Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. CoRR (2022)
Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, Florian Tramèr
What Does it Mean for a Language Model to Preserve Privacy? CoRR (2022)
Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, Taylor Berg-Kirkpatrick
Memorization in NLP Fine-tuning Methods. CoRR (2022)
Fatemehsadat Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick
Non-Parametric Temporal Adaptation for Social Media Topic Classification. CoRR (2022)
Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang, David Evans, Taylor Berg-Kirkpatrick
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models. EMNLP (2022)
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A. Inan, Lukas Wutschitz, Janardhan Kulkarni
Differentially Private Model Compression. CoRR (2022)
Fatemehsadat Mireshghallah, Kartik Goyal, Taylor Berg-Kirkpatrick
Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models. ACL (1) (2022)
Fatemehsadat Mireshghallah, Richard Shin, Yu Su, Tatsunori Hashimoto, Jason Eisner
Privacy-Preserving Domain Adaptation of Semantic Parsers. CoRR (2022)
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A. Inan, Lukas Wutschitz, Janardhan Kulkarni
Differentially Private Model Compression. NeurIPS (2022)
Rakshit Naidu, Aman Priyanshu, Aadith Kumar, Sasikanth Kotti, Haofan Wang, Fatemehsadat Mireshghallah
When Differential Privacy Meets Interpretability: A Case Study. CoRR (2021)
Teddy Koker, Fatemehsadat Mireshghallah, Tom Titcombe, Georgios Kaissis
U-Noise: Learnable Noise Masks for Interpretable Image Segmentation. ICIP (2021)
Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels. NAACL-HLT (2021)
Fatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness. EMNLP (1) (2021)
Fatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness. CoRR (2021)
Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah, Mohammad Malekzadeh
Efficient Hyperparameter Optimization for Differentially Private Deep Learning. CoRR (2021)
Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh, Patrik Joslin Kenfack, Fatemehsadat Mireshghallah, Andrew Trask
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy? CoRR (2021)
Priyam Basu, Tiasa Singha Roy, Rakshit Naidu, Zümrüt Müftüoglu, Sahib Singh, Fatemehsadat Mireshghallah
Benchmarking Differential Privacy and Federated Learning for BERT Models. CoRR (2021)
Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis. CoRR (2021)
Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models. CoRR (2021)
Teddy Koker, Fatemehsadat Mireshghallah, Tom Titcombe, Georgios Kaissis
U-Noise: Learnable Noise Masks for Interpretable Image Segmentation. CoRR (2021)
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali, Ahmed Taha Elthakeb, Dean M. Tullsen, Hadi Esmaeilzadeh
Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy. WWW (2021)
Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh, Andrew Trask
Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy. PPMLP@CCS (2020)
Ahmed T. Elthakeb, Prannoy Pilligundla, Fatemehsadat Mireshghallah, Amir Yazdanbakhsh, Hadi Esmaeilzadeh
ReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks. IEEE Micro 40 (5) (2020)
Ahmed T. Elthakeb, Prannoy Pilligundla, Fatemehsadat Mireshghallah, Tarek Elgindi, Charles-Alban Deledalle, Hadi Esmaeilzadeh
Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization. CoRR (2020)
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali, Ahmed Taha Elthakeb, Dean M. Tullsen, Hadi Esmaeilzadeh
A Principled Approach to Learning Stochastic Representations for Privacy in Deep Neural Inference. CoRR (2020)
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Ali Jalali, Dean M. Tullsen, Hadi Esmaeilzadeh
Shredder: Learning Noise Distributions to Protect Inference Privacy. ASPLOS (2020)
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh
Privacy in Deep Learning: A Survey. CoRR (2020)
Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh, Andrew Trask
Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy. CoRR (2020)
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani, Dean M. Tullsen, Hadi Esmaeilzadeh
Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge. CoRR (2019)
Fatemehsadat Mireshghallah, Mohammad Bakhshalipour, Mohammad Sadrosadati, Hamid Sarbazi-Azad
Energy-Efficient Permanent Fault Tolerance in Hard Real-Time Systems. IEEE Trans. Computers 68 (10) (2019)