相关论文: Bootstrap The Original Latent: Learning a Private …

The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale…

Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing…

Training on test-time data enables deep learning models to adapt to dynamic environmental changes, enhancing their practical applicability. Online adaptation from source to target domains is promising but it remains highly reliant on the…

Source-Free Domain Adaptation (SFDA) addresses the challenge of adapting a model to a target domain without access to the data of the source domain. Prevailing methods typically start with a source model pre-trained with full supervision…

Most previous unsupervised domain adaptation (UDA) methods for question answering(QA) require access to source domain data while fine-tuning the model for the target domain. Source domain data may, however, contain sensitive information and…

The various post-processing methods for deep-learning-based models, such as quantification, pruning, and fine-tuning, play an increasingly important role in artificial intelligence technology, with pre-train large models as one of the main…

Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data. While the Unified World Model (UWM) formulation…

Standard methods for differentially private training of deep neural networks replace back-propagated mini-batch gradients with biased and noisy approximations to the gradient. These modifications to training often result in a…

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the local model weights are shared among the clients for local…

We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix. Such black-box learning settings are ubiquitous, for example, when the learner only has query access to the metric of…

We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly…

Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative Adversarial…

Generating adversarial examples in a black-box setting retains a significant challenge with vast practical application prospects. In particular, existing black-box attacks suffer from the need for excessive queries, as it is non-trivial to…

Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches are reparameterization methods, which update a target…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilizing knowledge from multiple source-pretrained models to an unlabeled target domain…

A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…

In recent years, attention-based models have excelled across various domains but remain vulnerable to backdoor attacks, often from downloading or fine-tuning on poisoned datasets. Many current methods to mitigate backdoors in NLP models…

Privacy noise may negate the benefits of using adaptive optimizers in differentially private model training. Prior works typically address this issue by using auxiliary information (e.g., public data) to boost the effectiveness of adaptive…

Multi-source Domain Adaptation (MDA) seeks to adapt models trained on data from multiple labeled source domains to perform effectively on an unlabeled target domain data, assuming access to sources data. To address the challenges of model…