Search Results for author:
Found 15 papers, 11 papers with code
Large Language Models are Advanced Anonymizers
Recent work in privacy research on large language models has shown that they achieve near human-level performance at inferring personal data from real-world online texts.
From Principle to Practice: Vertical Data Minimization for Machine Learning
We propose a novel vertical DM (vDM) workflow based on data generalization, which by design ensures that no full-resolution client data is collected during training and deployment of models, benefiting client privacy by reducing the attack surface in case of a breach.
Beyond Memorization: Violating Privacy Via Inference with Large Language Models
In this work, we present the first comprehensive study on the capabilities of pretrained LLMs to infer personal attributes from text.
CuTS: Customizable Tabular Synthetic Data Generation
To ensure high synthetic data quality in the presence of custom specifications, CuTS is pre-trained on the original dataset and fine-tuned on a differentiable loss automatically derived from the provided specifications using novel relaxations.
FARE: Provably Fair Representation Learning with Practical Certificates
To produce a practical certificate, we develop and apply a statistical procedure that computes a finite sample high-confidence upper bound on the unfairness of any downstream classifier trained on FARE embeddings.
TabLeak: Tabular Data Leakage in Federated Learning
A successful attack for tabular data must address two key challenges unique to the domain: (i) obtaining a solution to a high-variance mixed discrete-continuous optimization problem, and (ii) enabling human assessment of the reconstruction as unlike for image and text data, direct human inspection is not possible.
Data Leakage in Federated Averaging
On the popular FEMNIST dataset, we demonstrate that on average we successfully recover >45% of the client's images from realistic FedAvg updates computed on 10 local epochs of 10 batches each with 5 images, compared to only <10% using the baseline.
LAMP: Extracting Text from Gradients with Language Model Priors
Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning.
Latent Space Smoothing for Individually Fair Representations
This enables us to learn individually fair representations that map similar individuals close together by using adversarial training to minimize the distance between their representations.
Bayesian Framework for Gradient Leakage
We demonstrate that existing leakage attacks can be seen as approximations of this optimal adversary with different assumptions on the probability distributions of the input data and gradients.
Fair Normalizing Flows
Fair representation learning is an attractive approach that promises fairness of downstream predictors by encoding sensitive data.
Robustness Certification for Point Cloud Models
In this work, we address this challenge and introduce 3DCertify, the first verifier able to certify the robustness of point cloud models.
On the Paradox of Certified Training
Certified defenses based on convex relaxations are an established technique for training provably robust models.
Efficient Certification of Spatial Robustness
Recent work has exposed the vulnerability of computer vision models to vector field attacks.
Learning Certified Individually Fair Representations
That is, our method enables the data producer to learn and certify a representation where for a data point all similar individuals are at $\ell_\infty$-distance at most $\epsilon$, thus allowing data consumers to certify individual fairness by proving $\epsilon$-robustness of their classifier.
