43 citations · 104 across the 12 of their papers we have counts for
12 papers
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin A. Inan +6
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the priv…
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A Inan +2
Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models…
What Does it Mean for a Language Model to Preserve Privacy?
Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah +2
Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context a…
When Differential Privacy Meets Interpretability: A Case Study
Rakshit Naidu, Aman Priyanshu, Aadith Kumar +3
Given the increase in the use of personal data for training Deep Neural Networks (DNNs) in tasks such as medical imaging and diagnosis, differentially private training of DNNs is s…
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
Archit Uniyal, Rakshit Naidu, Sasikanth Kotti +4
Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on dif…
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa +3
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such…
U-Noise: Learnable Noise Masks for Interpretable Image Segmentation
Teddy Koker, Fatemehsadat Mireshghallah, Tom Titcombe +1
Deep Neural Networks (DNNs) are widely used for decision making in a myriad of critical applications, ranging from medical to societal and even judicial. Given the importance of th…
Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh +1
Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often cro…
WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization
Ahmed T. Elthakeb, Prannoy Pilligundla, Fatemehsadat Mireshghallah +3
As deep neural networks make their ways into different domains, their compute efficiency is becoming a first-order constraint. Deep quantization, which reduces the bitwidth of the…
Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali +3
When receiving machine learning services from the cloud, the provider does not need to receive all features; in fact, only a subset of the features are necessary for the target pre…
Shredder: Learning Noise Distributions to Protect Inference Privacy
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Prakash Ramrakhyani +2
A wide variety of deep neural applications increasingly rely on the cloud to perform their compute-heavy inference. This common practice requires sending private and privileged dat…
ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
Ahmed T. Elthakeb, Prannoy Pilligundla, FatemehSadat Mireshghallah +2
Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN…