Related papers: Data-Chain Backdoor: Do You Trust Diffusion Models…

Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applications. A common…

In the domain of backdoor attacks, accurate labeling of injected data is essential for evading rudimentary detection mechanisms. This imperative has catalyzed the development of clean-label attacks, which are notably more elusive as they…

Machine learning (ML) has progressed rapidly during the past decade and the major factor that drives such development is the unprecedented large-scale data. As data generation is a continuous process, this leads to ML model owners updating…

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…

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,…

Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this…

Generating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self-driving cars. Traditional generative models rely on Markov chain methods and can produce accurate…

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated…

Model collapse, the severe degradation of generative models when iteratively trained on their own outputs, has gained significant attention in recent years. This paper examines Chain of Diffusion, where a pretrained text-to-image diffusion…

Synthetic data has been hailed as the silver bullet for privacy preserving data analysis. If a record is not real, then how could it violate a person's privacy? In addition, deep-learning based generative models are employed successfully to…

Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…

The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often struggle to generalize to unseen domains due to the diverse…

Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet daily, possibly containing backdoors, and third-party model…

Process data with confidential information cannot be shared directly in public, which hinders the research in process data mining and analytics. Data encryption methods have been studied to protect the data, but they still may be decrypted,…

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, additional…

Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising…

The widespread adoption of dynamic Time-of-Use (dToU) electricity tariffs requires accurately identifying households that would benefit from such pricing structures. However, the use of real consumption data poses serious privacy concerns,…

Graph Neural Networks (GNNs) have demonstrated strong performance across tasks such as node classification, link prediction, and graph classification, but remain vulnerable to backdoor attacks that implant imperceptible triggers during…

Synthetic samples from diffusion models are promising for leveraging in training discriminative models as replications of real training datasets. However, we found that the synthetic datasets degrade classification performance over real…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…