相关论文: Gradient Inversion Transcript: Leveraging Robust G…

The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversion attacks. Existing paradigms face a fundamental trade-off:…

Graph neural networks (GNNs) offer promising learning methods for graph-related tasks. However, GNNs are at risk of adversarial attacks. Two primary limitations of the current evasion attack methods are highlighted: (1) The current…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

Gradient descent is the method of choice for training large artificial intelligence systems. As these systems become larger, a better understanding of the mechanisms behind gradient training would allow us to alleviate compute costs and…

Interactive Intelligent Tutoring Systems (ITSs) enhance traditional ITSs by promoting effective learning through interactions and problem resolution in online education. Yet, proactive engagement, prioritizing resource optimization with…

Understanding when and how much a model gradient leaks information about the training sample is an important question in privacy. In this paper, we present a surprising result: even without training or memorizing the data, we can fully…

Performative Drift is a special type of Concept Drift that occurs when a model's predictions influence the future instances the model will encounter. In these settings, retraining is not always feasible. In this work, we instead focus on…

Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed set of documents (static corpora). However, in realistic scenarios, this is rarely the case and the documents to be retrieved are constantly updated…

Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy…

Inferring the latent variable generating a given test sample is a challenging problem in Generative Adversarial Networks (GANs). In this paper, we propose InvGAN - a novel framework for solving the inference problem in GANs, which involves…

We introduceGraphGPT, a novel self-supervised generative pre-trained model for graph learning based on the Graph Eulerian Transformer (GET). First, we propose GET, which combines a standard transformer encoder or decoder architecture with…

Recently deep generative models have achieved impressive progress in modeling the distribution of training data. In this work, we present for the first time a generative model for 4D light field patches using variational autoencoders to…

To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data before training starts. In this paper, we explore strategies…

Distributed training methods are crucial for large language models (LLMs). However, existing distributed training methods often suffer from communication bottlenecks, stragglers, and limited elasticity, particularly in heterogeneous or…

Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning. While success was demonstrated primarily on image data, these methods do not directly transfer to…

Current studies on adversarial robustness mainly focus on aggregating local robustness results from a set of data samples to evaluate and rank different models. However, the local statistics may not well represent the true global robustness…

Vision transformers (ViTs) have been successfully deployed in a variety of computer vision tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local model to generate adversarial samples and directly…

While generative models have proved successful in many domains, they may pose a privacy leakage risk in practical deployment. To address this issue, differentially private generative model learning has emerged as a solution to train private…

Adversarial training (AT) is considered the most effective defense against adversarial attacks. However, a recent study revealed that \(\ell_{\infty}\)-norm adversarial training (\(\ell_{\infty}\)-AT) will also induce unevenly distributed…

Designing models that produce accurate predictions is the fundamental objective of machine learning (ML). This work presents methods demonstrating that when the derivatives of target variables (outputs) with respect to inputs can be…