activity
20122021
most citedTraining Data Leakage Analysis in Language Models

22 citations · 43 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CL202114 cited

Membership Inference on Word Embedding and Beyond

Saeed Mahloujifar, Huseyin A. Inan, Melissa Chase +2

In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In som…

cs.CR2021

On Privacy and Confidentiality of Communications in Organizational Graphs

Masoumeh Shafieinejad, Huseyin Inan, Marcello Hasegawa +1

Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended…

cs.LG20215 cited

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…

cs.CR202122 cited

Training Data Leakage Analysis in Language Models

Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz +4

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated t…

cs.LG2020

rTop-k: A Statistical Estimation Approach to Distributed SGD

Leighton Pate Barnes, Huseyin A. Inan, Berivan Isik +1

The large communication cost for exchanging gradients between different nodes significantly limits the scalability of distributed training for large-scale learning models. Motivate…

cs.CL20192 cited

Improving Semantic Parsing with Neural Generator-Reranker Architecture

Huseyin A. Inan, Gaurav Singh Tomar, Huapu Pan

Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have re…