Search Results for author:
Found 21 papers, 8 papers with code
pfl-research: simulation framework for accelerating research in Private Federated Learning
Federated learning (FL) is an emerging machine learning (ML) training paradigm where clients own their data and collaborate to train a global model, without revealing any data to the server and other participants.
Momentum Approximation in Asynchronous Private Federated Learning
Asynchronous protocols have been shown to improve the scalability of federated learning (FL) with a massive number of clients.
Samplable Anonymous Aggregation for Private Federated Data Analysis
We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data.
Population Expansion for Training Language Models with Private Federated Learning
Federated learning (FL) combined with differential privacy (DP) offers machine learning (ML) training with distributed devices and with a formal privacy guarantee.
FLAIR: Federated Learning Annotated Image Repository
We believe FLAIR can serve as a challenging benchmark for advancing the state-of-the art in federated learning.
Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Our goal is to train a large neural network language model (NNLM) on compute-constrained devices while preserving privacy using FL and DP.
Training a Tokenizer for Free with Private Federated Learning
During private federated learning of the language model, we sample from the model, train a new tokenizer on the sampled sequences, and update the model embeddings.
Adversarial Semantic Collisions
We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models.
You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion
We demonstrate that neural code autocompleters are vulnerable to poisoning attacks.
Information Leakage in Embedding Models
We demonstrate that embeddings, in addition to encoding generic semantics, often also present a vector that leaks sensitive information about the input data.
Generalized Zero-shot ICD Coding
The International Classification of Diseases (ICD) is a list of classification codes for the diagnoses.
Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning
In this paper, we present \emph{membership encoding} for training deep neural networks and encoding the membership information, i. e. whether a data point is used for training, for a subset of training data.
Overlearning Reveals Sensitive Attributes
For example, a binary gender classifier of facial images also learns to recognize races\textemdash even races that are not represented in the training data\textemdash and identities.
Auditing Data Provenance in Text-Generation Models
To help enforce data-protection regulations such as GDPR and detect unauthorized uses of personal data, we develop a new \emph{model auditing} technique that helps users check if their data was used to train a machine learning model.
Exploiting Unintended Feature Leakage in Collaborative Learning
First, we show that an adversarial participant can infer the presence of exact data points -- for example, specific locations -- in others' training data (i. e., membership inference).
Chiron: Privacy-preserving Machine Learning as a Service
Existing ML-as-a-service platforms require users to reveal all training data to the service operator.
Cryptography and Security
Fooling OCR Systems with Adversarial Text Images
We demonstrate that state-of-the-art optical character recognition (OCR) based on deep learning is vulnerable to adversarial images.
Kernel Distillation for Fast Gaussian Processes Prediction
Gaussian processes (GPs) are flexible models that can capture complex structure in large-scale dataset due to their non-parametric nature.
Machine Learning Models that Remember Too Much
In this setting, we design and implement practical algorithms, some of them very similar to standard ML techniques such as regularization and data augmentation, that "memorize" information about the training dataset in the model yet the model is as accurate and predictive as a conventionally trained model.
Membership Inference Attacks against Machine Learning Models
We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained.
Learning Genomic Representations to Predict Clinical Outcomes in Cancer
Genomics are rapidly transforming medical practice and basic biomedical research, providing insights into disease mechanisms and improving therapeutic strategies, particularly in cancer.
