Search Results for author:
Found 12 papers, 2 papers with code
CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data
Advances in generative AI point towards a new era of personalized applications that perform diverse tasks on behalf of users.
Operationalizing Contextual Integrity in Privacy-Conscious Assistants
To steer information-sharing assistants to behave in accordance with privacy expectations, we propose to operationalize contextual integrity (CI), a framework that equates privacy with the appropriate flow of information in a given context.
AirGapAgent: Protecting Privacy-Conscious Conversational Agents
The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns.
Explainable AI for survival analysis: a median-SHAP approach
With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications.
Differentially Private Statistical Inference through $β$-Divergence One Posterior Sampling
To ameliorate this, we propose $\beta$D-Bayes, a posterior sampling scheme from a generalised posterior targeting the minimisation of the $\beta$-divergence between the model and the data generating process.
A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods
We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods.
AIRIVA: A Deep Generative Model of Adaptive Immune Repertoires
Recent advances in immunomics have shown that T-cell receptor (TCR) signatures can accurately predict active or recent infection by leveraging the high specificity of TCR binding to disease antigens.
Differentially Private Diffusion Models Generate Useful Synthetic Images
By privately fine-tuning ImageNet pre-trained diffusion models with more than 80M parameters, we obtain SOTA results on CIFAR-10 and Camelyon17 in terms of both FID and the accuracy of downstream classifiers trained on synthetic data.
Quasi-Bayesian Nonparametric Density Estimation via Autoregressive Predictive Updates
In the context of density estimation, the standard nonparametric Bayesian approach is to target the posterior predictive of the Dirichlet process mixture model.
Mitigating Statistical Bias within Differentially Private Synthetic Data
Increasing interest in privacy-preserving machine learning has led to new and evolved approaches for generating private synthetic data from undisclosed real data.
On Locality of Local Explanation Models
Empirically, we observe that Neighbourhood Shapley values identify meaningful sparse feature relevance attributions that provide insight into local model behaviour, complimenting conventional Shapley analysis.
Deep Generative Pattern-Set Mixture Models for Nonignorable Missingness
We propose a variational autoencoder architecture to model both ignorable and nonignorable missing data using pattern-set mixtures as proposed by Little (1993).
