相关论文: SOPHON: Non-Fine-Tunable Learning to Restrain Task…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or…

Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces. However, model extraction attacks threaten these assets by enabling unauthorized source-domain…

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature…

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples. The attacked model behaves normally on benign…

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However,…

Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data. Motivated by the effectiveness and robustness of…

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models that are safe to deploy. Despite its clear importance, there…

Robot task planning is an important problem for autonomous robots in long-horizon challenging tasks. As large pre-trained models have demonstrated superior planning ability, recent research investigates utilizing large models to achieve…

Differentially Private Federated Learning (DPFL) strengthens privacy protection by perturbing model gradients with noise, though at the cost of reduced accuracy. Although prior empirical studies indicate that initializing from pre-trained…

Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks.…

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…

Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To…

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…