相关论文: Auditing Information Disclosure During LLM-Scale G…

The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for…

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for handling such data and…

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

The interplay between optimization and privacy has become a central theme in privacy-preserving machine learning. Noisy stochastic gradient descent (SGD) has emerged as a cornerstone algorithm, particularly in large-scale settings. These…

Differentially private gradient descent (DP-GD) is a popular algorithm to train deep learning models with provable guarantees on the privacy of the training data. In the last decade, the problem of understanding its performance cost with…

High-stakes domains like cyber operations need responsible and trustworthy AI methods. While large language models (LLMs) are becoming increasingly popular in these domains, they still suffer from hallucinations. This research paper…

We analyse the privacy leakage of noisy stochastic gradient descent by modeling R\'enyi divergence dynamics with Langevin diffusions. Inspired by recent work on non-stochastic algorithms, we derive similar desirable properties in the…

The Gaussian Mechanism (GM), which consists in adding Gaussian noise to a vector-valued query before releasing it, is a standard privacy protection mechanism. In particular, given that the query respects some L2 sensitivity property (the L2…

Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsible LLMs. In addition to verbalising the confidence by LLM self-report, more recent methods…

Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the…

Spiking neural networks (SNNs) have emerged as prominent candidates for embedded and edge AI. Their inherent low power consumption makes them far more efficient than conventional ANNs in scenarios where energy budgets are tightly…

We consider the problem of empirical risk minimization given a database, using the gradient descent algorithm. We note that the function to be optimized may be non-convex, consisting of saddle points which impede the convergence of the…

Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GIAs), which recover…

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak sensitive information about the underlying data, raising…

We propose Gradient Inversion Transcript (GIT), a novel generative approach for reconstructing training data from leaked gradients. GIT employs a generative attack model, whose architecture is tailored to align with the structure of the…

Federated learning of deep learning models for supervised tasks, e.g. image classification and segmentation, has found many applications: for example in human-in-the-loop tasks such as film post-production where it enables sharing of domain…

While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach…