Natural attack for pre-trained models of code
Pre-trained models of code have achieved success in many important software engineering
tasks. However, these powerful models are vulnerable to adversarial attacks that slightly …
tasks. However, these powerful models are vulnerable to adversarial attacks that slightly …
Stealthy backdoor attack for code models
Code models, such as CodeBERT and CodeT5, offer general-purpose representations of
code and play a vital role in supporting downstream automated software engineering tasks …
code and play a vital role in supporting downstream automated software engineering tasks …
Curiosity-driven and victim-aware adversarial policies
Recent years have witnessed great potential in applying Deep Reinforcement Learning
(DRL) in various challenging applications, such as autonomous driving, nuclear fusion …
(DRL) in various challenging applications, such as autonomous driving, nuclear fusion …
Deepgd: A multi-objective black-box test selection approach for deep neural networks
Deep neural networks (DNNs) are widely used in various application domains such as
image processing, speech recognition, and natural language processing. However, testing …
image processing, speech recognition, and natural language processing. However, testing …
Towards fair machine learning software: Understanding and addressing model bias through counterfactual thinking
The increasing use of Machine Learning (ML) software can lead to unfair and unethical
decisions, thus fairness bugs in software are becoming a growing concern. Addressing …
decisions, thus fairness bugs in software are becoming a growing concern. Addressing …
What do users ask in open-source AI repositories? An empirical study of GitHub issues
Artificial Intelligence (AI) systems, which benefit from the availability of large-scale datasets
and increasing computational power, have become effective solutions to various critical …
and increasing computational power, have become effective solutions to various critical …
Evaluating the robustness of test selection methods for deep neural networks
Testing deep learning-based systems is crucial but challenging due to the required time and
labor for labeling collected raw data. To alleviate the labeling effort, multiple test selection …
labor for labeling collected raw data. To alleviate the labeling effort, multiple test selection …
Can Coverage Criteria Guide Failure Discovery for Image Classifiers? An Empirical Study
Quality assurance of deep neural networks (DNNs) is crucial for the deployment of DNN-
based software, especially in mission-and safety-critical tasks. Inspired by structural white …
based software, especially in mission-and safety-critical tasks. Inspired by structural white …
Dream: Debugging and repairing automl pipelines
Deep Learning models have become an integrated component of modern software systems.
In response to the challenge of model design, researchers proposed Automated Machine …
In response to the challenge of model design, researchers proposed Automated Machine …
Prioritizing speech test cases
As automated speech recognition (ASR) systems gain widespread acceptance, there is a
pressing need to rigorously test and enhance their performance. Nonetheless, the process …
pressing need to rigorously test and enhance their performance. Nonetheless, the process …