Related papers: MEGA: Model Stealing via Collaborative Generator-S…

Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a…

Imitation learning is a powerful paradigm for training robotic policies, yet its performance is limited by compounding errors: minor policy inaccuracies could drive robots into unseen out-of-distribution (OOD) states in the training set,…

Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily…

Calibration of neural networks is a topical problem that is becoming more and more important as neural networks increasingly underpin real-world applications. The problem is especially noticeable when using modern neural networks, for which…

Acquiring large quantities of data and annotations is known to be effective for developing high-performing deep learning models, but is difficult and expensive to do in the healthcare context. Adding synthetic training data using generative…

Datasets with missing values are very common in real world applications. GAIN, a recently proposed deep generative model for missing data imputation, has been proved to outperform many state-of-the-art methods. But GAIN only uses a…

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving…

We typically compute aggregate statistics on held-out test data to assess the generalization of machine learning models. However, statistics on test data often overstate model generalization, and thus, the performance of deployed machine…

It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples…

Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent…

Recently, generative machine-learning models have gained popularity in physics, driven by the goal of improving the efficiency of Markov chain Monte Carlo techniques and of exploring their potential in capturing experimental data…

An off-the-shelf model as a commercial service could be stolen by model stealing attacks, posing great threats to the rights of the model owner. Model fingerprinting aims to verify whether a suspect model is stolen from the victim model,…

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…

Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output…

Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for…

Graph Few-Shot Class-Incremental Learning (GFSCIL) enables models to continually learn from limited samples of novel tasks after initial training on a large base dataset. Existing GFSCIL approaches typically utilize Prototypical Networks…

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…

Deep learning has achieved enormous success in various industrial applications. Companies do not want their valuable data to be stolen by malicious employees to train pirated models. Nor do they wish the data analyzed by the competitors…

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…