Search Results for author:
Found 30 papers, 6 papers with code
Duwak: Dual Watermarks in Large Language Models
As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms.
Quantifying and Mitigating Privacy Risks for Tabular Generative Models
The backbone technology of tabular synthesizers is rooted in image generative models, ranging from Generative Adversarial Networks (GANs) to recent diffusion models.
The Rise of Diffusion Models in Time-Series Forecasting
This survey delves into the application of diffusion models in time-series forecasting.
CDGraph: Dual Conditional Social Graph Synthesizing via Diffusion Model
The social graphs synthesized by the generative models are increasingly in demand due to data scarcity and concerns over user privacy.
BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise
We show that the accuracy of Reptile, iMAML, and foMAML drops by up to 42% on the Omniglot and CifarFS datasets when meta-training is affected by label noise.
GTV: Generating Tabular Data via Vertical Federated Learning
Conditional vector for tabular GANs is a valuable tool to control specific features of generated data.
Permutation-Invariant Tabular Data Synthesis
We show that changing the input column order worsens the statistical difference between real and synthetic data by up to 38. 67% due to the encoding of tabular data and the network architectures.
Aergia: Leveraging Heterogeneity in Federated Learning Systems
Federated Learning (FL) is a popular approach for distributed deep learning that prevents the pooling of large amounts of data in a central server.
FCT-GAN: Enhancing Table Synthesis via Fourier Transform
Mainstream state-of-the-art tabular data synthesizers draw methodologies from Generative Adversarial Networks (GANs), which are composed of a generator and a discriminator.
AGIC: Approximate Gradient Inversion Attack on Federated Learning
Recent reconstruction attacks apply a gradient inversion optimization on the gradient update of a single minibatch to reconstruct the private data used by clients during training.
Federated Geometric Monte Carlo Clustering to Counter Non-IID Datasets
Federated learning allows clients to collaboratively train models on datasets that are acquired in different locations and that cannot be exchanged because of their size or regulations.
CTAB-GAN+: Enhancing Tabular Data Synthesis
We extensively evaluate CTAB-GAN+ on data similarity and analysis utility against state-of-the-art tabular GANs.
Fabricated Flips: Poisoning Federated Learning without Data
Consequently, we design REFD, a defense specifically crafted to protect against data-free attacks.
MEGA: Model Stealing via Collaborative Generator-Substitute Networks
However, they are all based on competing generator-substitute networks and hence encounter training instability. In this paper we propose a data-free model stealing frame-work, MEGA, which is based on collaborative generator-substitute networks and only requires the target model toprovide label prediction for synthetic query examples.
Attacks and Defenses for Free-Riders in Multi-Discriminator GAN
To mitigate the model degradation, we propose a defense strategy against free-riders in MD-GAN, termed DFG.
LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision
The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics.
Confident Data-free Model Stealing for Black-box Adversarial Attacks
Deep machine learning models are increasingly deployed in the wild, subject to adversarial attacks.
Fed-TGAN: Federated Learning Framework for Synthesizing Tabular Data
And, while learning GANs to synthesize images on FL systems has just been demonstrated, it is unknown if GANs for tabular data can be learned from decentralized data sources.
Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators
Multi-label learning is an emerging extension of the multi-class classification where an image contains multiple labels.
Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning
Shapley Value is commonly adopted to measure and incentivize client participation in federated learning.
Enhancing Robustness of On-line Learning Models on Highly Noisy Data
Classification algorithms have been widely adopted to detect anomalies for various systems, e. g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i. e., features and labels are correctly set.
CTAB-GAN: Effective Table Data Synthesizing
In this paper, we develop CTAB-GAN, a novel conditional table GAN architecture that can effectively model diverse data types, including a mix of continuous and categorical variables.
Robust Learning via Golden Symmetric Loss of (un)Trusted Labels
In this paper, we propose to construct a golden symmetric loss (GSL) based on the estimated confusion matrix as to avoid overfitting to noisy labels and learn effectively from hard classes.
End-to-End Learning from Noisy Crowd to Supervised Machine Learning Models
Furthermore, relabeling only 10% of the data using the expert's results in over 90% classification accuracy with SVM.
Active Learning for Noisy Data Streams Using Weak and Strong Labelers
Labeling data correctly is an expensive and challenging task in machine learning, especially for on-line data streams.
TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise
Based on the insights, we design TrustNet that first adversely learns the pattern of noise corruption, being it both symmetric or asymmetric, from a small set of trusted data.
ExpertNet: Adversarial Learning and Recovery Against Noisy Labels
Today's available datasets in the wild, e. g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i. e. erroneous, labels.
QActor: On-line Active Learning for Noisy Labeled Stream Data
A central feature of QActor is to dynamically adjust the query limit according to the learning loss for each data batch.
RAD: On-line Anomaly Detection for Highly Unreliable Data
Classification algorithms have been widely adopted to detect anomalies for various systems, e. g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i. e., features and labels are correctly set.
Online Label Aggregation: A Variational Bayesian Approach
Our evaluation results on various online scenarios show that BiLA can effectively infer the true labels, with an error rate reduction of at least 10 to 1. 5 percent points for synthetic and real-world datasets, respectively.
