Search Results for author:
Found 22 papers, 5 papers with code
Privacy Leakage in Text Classification A Data Extraction Approach
Recent work has demonstrated the successful extraction of training data from generative language models.
Differentially Private Training of Mixture of Experts Models
This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing.
Privately Aligning Language Models with Reinforcement Learning
Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT.
Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation
Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind.
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Our results demonstrate that our algorithm can achieve competitive performance with strong privacy levels.
Project Florida: Federated Learning Made Easy
Federated learning enables model training across devices and silos while the training data remains within its security boundary, by distributing a model snapshot to a client running inside the boundary, running client code to update the model, and then aggregating updated snapshots across many clients in a central orchestrator.
FedJETs: Efficient Just-In-Time Personalization with Federated Mixture of Experts
Our gating function harnesses the knowledge of a pretrained model common expert to enhance its routing decisions on-the-fly.
Analyzing Leakage of Personally Identifiable Information in Language Models
Understanding the risk of LMs leaking Personally Identifiable Information (PII) has received less attention, which can be attributed to the false assumption that dataset curation techniques such as scrubbing are sufficient to prevent PII leakage.
TrojanPuzzle: Covertly Poisoning Code-Suggestion Models
To achieve this, prior attacks explicitly inject the insecure code payload into the training data, making the poison data detectable by static analysis tools that can remove such malicious data from the training set.
Federated Multilingual Models for Medical Transcript Analysis
Federated Learning (FL) is a novel machine learning approach that allows the model trainer to access more data samples, by training the model across multiple decentralized data sources, while data access constraints are in place.
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data.
Privacy Leakage in Text Classification: A Data Extraction Approach
Recent work has demonstrated the successful extraction of training data from generative language models.
Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning
In this work, we propose a novel ensemble knowledge transfer method named Fed-ET in which small models (different in architecture) are trained on clients, and used to train a larger model at the server.
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
We compare the platform with other state-of-the-art platforms and describe available features of FLUTE for experimentation in core areas of active research, such as optimization, privacy, and scalability.
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
As such, these models are often unable to produce personalized responses for individual users, based on their data.
Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets
Auditing NLP systems for computational harms like surfacing stereotypes is an elusive goal.
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a novel triplet-loss term.
On Privacy and Confidentiality of Communications in Organizational Graphs
We propose a model that captures the correlation in the social network graph, and incorporates this correlation in the privacy calculations through Pufferfish privacy principles.
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a triplet-loss term.
Training Data Leakage Analysis in Language Models
It has been demonstrated that strong performance of language models comes along with the ability to memorize rare training samples, which poses serious privacy threats in case the model is trained on confidential user content.
Leveraging Structured Metadata for Improving Question Answering on the Web
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
Conversations with Documents. An Exploration of Document-Centered Assistance
Our contributions are three-fold: (1) We first present a survey to understand the space of document-centered assistance and the capabilities people expect in this scenario.
