Related papers: DeepObfusCode: Source Code Obfuscation Through Seq…

We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While…

In the machine learning fields, Recurrent Neural Network (RNN) has become a popular architecture for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and…

To avoid detection, adversaries often use command-line obfuscation. There are numerous techniques of the command-line obfuscation, all designed to alter the command-line syntax without affecting its original functionality. This variability…

Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links…

Large language models generate code one token at a time. Their autoregressive generation process lacks the feedback of observing the program's output. Training LLMs to suggest edits directly can be challenging due to the scarcity of rich…

Recent years have seen the successful application of large pre-trained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application…

Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significant performance in this field, they are limited by their…

When evaluating the performance of a pre-trained model transferred to a downstream task, it is imperative to assess not only the in-distribution (ID) accuracy of the downstream model but also its capacity to generalize and identify…

Several types of AL-FEC (Application-Level FEC) codes for the Packet Erasure Channel exist. Random Linear Codes (RLC), where redundancy packets consist of random linear combinations of source packets over a certain finite field, are a…

Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition. We study the related issue of receiving…

In this paper, we propose a mechanism for storing complex patterns within a neural network and subsequently recalling them. This model is based on our work published in 2018(Inazawa, 2018), which we have refined and extended in this work.…

Code Large Language Models (LLMs) have demonstrated remarkable capabilities in generating, understanding, and manipulating programming code. However, their training process inadvertently leads to the memorization of sensitive information,…

The recurrent neural networks (RNN) can be used to solve the sequence to sequence problem, where both the input and the output have sequential structures. Usually there are some implicit relations between the structures. However, it is hard…

An effective and efficient encoding of the source code of a computer program is critical to the success of sequence-to-sequence deep neural network models for tasks in computer program comprehension, such as automated code summarization and…

Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-explored due to the…

Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners.…

With the rapid development of natural language processing technologies, more and more text steganographic methods based on automatic text generation technology have appeared in recent years. These models use the powerful self-learning and…

Open Source Software (OSS) security and resilience are worldwide phenomena hampering economic and technological innovation. OSS vulnerabilities can cause unauthorized access, data breaches, network disruptions, and privacy violations,…

Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing…

This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data…