相关论文: Code Membership Inference for Detecting Unauthoriz…

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is…

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…

Diffusion Models (DMs) benefit from large and diverse datasets for their training. Since this data is often scraped from the Internet without permission from the data owners, this raises concerns about copyright and intellectual property…

As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference…

With a growing focus on morphological inflection systems for languages where high-quality data is scarce, training data noise is a serious but so far largely ignored concern. We aim at closing this gap by investigating the types of noise…

Recent advancements in code large language models (Code-LLMs) have demonstrated remarkable capabilities in resolving programming related tasks. Meanwhile, researchers have recognized that the quality of pre-training data is crucial for…

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…

This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. Specifically, we propose two MINT architectures designed to learn the…

When learning to code, students often develop misconceptions about various programming language concepts. These can not only lead to bugs or inefficient code, but also slow down the learning of related concepts. In this paper, we introduce…

Code Smell, similar to a bad smell, is a surface indication of something tainted but in terms of software writing practices. This metric is an indication of a deeper problem lies within the code and is associated with an issue which is…

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…

This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling (BIM) by introducing a Large Language Model (LLM)-driven approach to semi-automate this critical process.…

Large Language Models (LLMs) represent a leap in artificial intelligence, excelling in tasks using human language(s). Although the main focus of general-purpose LLMs is not code generation, they have shown promising results in the domain.…

While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i.e., in-file context, but ignore the rich semantics in other files within…

We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy…

Pre-trained code models rely heavily on high-quality pre-training data, particularly human-written reference comments that bridge code and natural language. However, these comments often become outdated as software evolves, degrading model…

Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets…

Vulnerability detection is garnering increasing attention in software engineering, since code vulnerabilities possibly pose significant security. Recently, reusing various code pre-trained models has become common for code embedding without…

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright abuses. We show that models with higher dimensional input and output are more vulnerable to MIA, and…