相关论文: Generative Poisoning Using Random Discriminators

Conditional generative models, particularly diffusion-based methods, have recently been applied to graph prediction by modeling the target as a conditional distribution given the input graph, yielding competitive results compared to…

The Generative Adversarial Network (GAN) was recently introduced in the literature as a novel machine learning method for training generative models. It has many applications in statistics such as nonparametric clustering and nonparametric…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with either enhanced fidelity or increased diversity. Our approach involves manipulating the distribution of training and…

Current deep networks are very data-hungry and benefit from training on largescale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as…

Generative models (e.g., GANs, diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a particular region of the output space or sampling evenly over…

Federated learning (FL) is vulnerable to data poisoning attacks due to its distributed nature. Although recent GAN-based data poisoning methods have indicated the potential of using generative AI to generate seemingly legitimate poisoned…

In this paper a data mining approach for variable selection and knowledge extraction from datasets is presented. The approach is based on unguided symbolic regression (every variable present in the dataset is treated as the target variable…

High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in…

The design of mean and variance schedules for the perturbed signal is a fundamental challenge in generative models. While score-based and Schr\"odinger bridge-based models require careful selection of the stochastic differential equation to…

Retrieval-Augmented Generation (RAG) empowers Large Language Models (LLMs) to dynamically integrate external knowledge during inference, improving their factual accuracy and adaptability. However, adversaries can inject poisoned external…

Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for…

Imitation learning is a promising paradigm for training robot control policies, but these policies can suffer from distribution shift, where the conditions at evaluation time differ from those in the training data. A popular approach for…

Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones. In this work, we…

In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this…

Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted…

There is growing consensus among neuroscientists that neural circuits critical for survival are the result of genomic decompression processes. We introduce SynaptoGen, a novel computational framework--member of the Connectome Models…

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to…

Path planning in complex environments is one of the key problems of artificial intelligence because it requires simultaneous understanding of the geometry of space and the global structure of the problem. In this paper, we explore the…

Sponge attacks aim to increase the energy consumption and computation time of neural networks. In this work, we present a novel sponge attack called SkipSponge. SkipSponge is the first sponge attack that is performed directly on the…