相关论文: Provable Training Data Identification for Large La…

Large-scale pre-trained models have achieved remarkable success in many applications, but how to leverage them to improve the prediction reliability of downstream models is undesirably under-explored. Moreover, modern neural networks have…

In this paper, we aim to improve the performance of in-the-wild Facial Expression Recognition (FER) by exploiting semi-supervised learning. Large-scale labeled data and deep learning methods have greatly improved the performance of image…

In the rapidly evolving semiconductor industry, where research, design, verification, and manufacturing are intricately linked, the potential of Large Language Models to revolutionize hardware design and security verification is immense.…

Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm has been especially…

Vulnerability analysis is crucial for software security. This work focuses on using pre-training techniques to enhance the understanding of vulnerable code and boost vulnerability analysis. The code understanding ability of a pre-trained…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Differential Privacy (DP) is the de facto standard for reasoning about the privacy guarantees of a training algorithm. Despite the empirical observation that DP reduces the vulnerability of models to existing membership inference (MI)…

Recently, deep self-training approaches emerged as a powerful solution to the unsupervised domain adaptation. The self-training scheme involves iterative processing of target data; it generates target pseudo labels and retrains the network.…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

Deep neural networks are susceptible to backdoor attacks, where adversaries manipulate model predictions by inserting malicious samples into the training data. Currently, there is still a significant challenge in identifying suspicious…

Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like…

The scarcity of high-quality labeled data in sensor-based Human Activity Recognition (HAR) hinders model performance and limits generalization across real-world scenarios. Data augmentation is a key strategy to mitigate this issue by…

Preserving privacy in sensitive data while pretraining large language models on small, domain-specific corpora presents a significant challenge. In this work, we take an exploratory step toward privacy-preserving continual pretraining by…

Effective prioritization of issue reports is crucial in software engineering to optimize resource allocation and address critical problems promptly. However, the manual classification of issue reports for prioritization is laborious and…

Although Shapley values have been shown to be highly effective for identifying harmful training instances, dataset size and model complexity constraints limit the ability to apply Shapley-based data valuation to fine-tuning large…

The value and copyright of training data are crucial in the artificial intelligence industry. Service platforms should protect data providers' legitimate rights and fairly reward them for their contributions. Shapley value, a potent tool…

Data-driven control offers a viable option for control scenarios where constructing a system model is expensive or time-consuming. Nonetheless, many of these algorithms are not entirely automated, often necessitating the adjustment of…

Transfer learning (TL) for high-dimensional regression (HDR) is an important problem in machine learning, particularly when dealing with limited sample size in the target task. However, there currently lacks a method to quantify the…

This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are…

Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…