Related papers: CodeAttack: Code-Based Adversarial Attacks for Pre…

Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven by local heuristic…

Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Recent developments in binary-level foundation models suggest a…

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

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…

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, currently there is no study of their robustness to adversarial attacks. Yet, in domains where they are likely…

Foundation models (e.g., CodeBERT, GraphCodeBERT, CodeT5) work well for many software engineering tasks. These models are pre-trained (using self-supervision) with billions of code tokens, and then fine-tuned with hundreds of thousands of…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…

Software Engineering (SE) Pre-trained Language Models (PLMs), such as CodeBERT, are pre-trained on large code corpora, and their learned knowledge has shown success in transferring into downstream tasks (e.g., code clone detection) through…

Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large…

In the era of rapid advancements in artificial intelligence (AI), neural network models have achieved notable breakthroughs. However, concerns arise regarding their vulnerability to adversarial attacks. This study focuses on enhancing…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Recent studies have demonstrated outstanding capabilities of large language models (LLMs) in software engineering tasks, including code generation and comprehension. While LLMs have shown significant potential in assisting with coding, LLMs…

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision applications. However, studies have shown that, like…

Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or more task-specific…

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code…