Related papers: Untargeted Code Authorship Evasion with Seq2Seq Tr…

We consider the task of mapping pseudocode to long programs that are functionally correct. Given test cases as a mechanism to validate programs, we search over the space of possible translations of the pseudocode to find a program that…

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…

In an era where cyberattacks increasingly target the software supply chain, the ability to accurately attribute code authorship in binary files is critical to improving cybersecurity measures. We propose OCEAN, a contrastive learning-based…

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations…

The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of online authorship when needed, e.g., blind reviews for…

Learning rich data representations from unlabeled data is a key challenge towards applying deep learning algorithms in downstream tasks. Several variants of variational autoencoders (VAEs) have been proposed to learn compact data…

Recently, there has been a growing interest in automatic software vulnerability detection. Pre-trained model-based approaches have demonstrated superior performance than other Deep Learning (DL)-based approaches in detecting…

During software maintenance, programmers spend a lot of time on code comprehension. Reading comments is an effective way for programmers to reduce the reading and navigating time when comprehending source code. Therefore, as a critical task…

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…

We propose TRACE, a structure-aware framework leveraging diffusion models for localized character encoding to embed data. Unlike existing methods that rely on edge features or pre-defined codebooks, TRACE exploits character structures that…

Most existing pre-trained language models for source code focus on learning the static code text, typically augmented with static code structures (abstract syntax tree, dependency graphs, etc.). However, program semantics will not be fully…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

Side-channel attacks impose a serious threat to cryptographic algorithms, including widely employed ones, such as AES and RSA. These attacks take advantage of the algorithm implementation in hardware or software to extract secret…

Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular…

Source code plagiarism detection is a problem that has been addressed several times before; and several tools have been developed for that purpose. In this research project we investigated a set of possible disguises that can be…

The pre-trained speech encoder wav2vec 2.0 performs very well on various spoken language understanding (SLU) tasks. However, on many tasks, it trails behind text encoders with textual input. To improve the understanding capability of SLU…

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

Occlusion in face recognition is a common yet challenging problem. While sparse representation based classification (SRC) has been shown promising performance in laboratory conditions (i.e. noiseless or random pixel corrupted), it performs…

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak…

Static program slicing is a fundamental technique in software engineering. Traditional static slicing tools rely on parsing complete source code, which limits their applicability to real-world scenarios where code snippets are incomplete or…