163 citations · 493 across the 35 of their papers we have counts for
9 papers · 1 filter
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
Chen Gong, Zhou Yang, Yunpeng Bai +8
Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL…
Answer Summarization for Technical Queries: Benchmark and New Approach
Yang Chengran, Bowen Xu, Ferdian Thung +8
Prior studies have demonstrated that approaches to generate an answer summary for a given technical query in Software Question and Answer (SQA) sites are desired. We find that exis…
Compressing Pre-trained Models of Code into 3 MB
Jieke Shi, Zhou Yang, Bowen Xu +2
Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these…
Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks
Zhenxiong Miao, Xingshu Chen, Haizhou Wang +3
The pervasiveness of offensive language on the social network has caused adverse effects on society, such as abusive behavior online. It is urgent to detect offensive language and…
PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models
Junda He, Bowen Xu, Zhou Yang +3
Stack Overflow is often viewed as the most influential Software Question Answer (SQA) website with millions of programming-related questions and answers. Tags play a critical role…
Natural Attack for Pre-trained Models of Code
Zhou Yang, Jieke Shi, Junda He +1
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 pe…
Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?
chengran Yang, Bowen Xu, Junaed younus Khan +4
APIs (Application Programming Interfaces) are reusable software libraries and are building blocks for modern rapid software development. Previous research shows that programmers fr…
Can Identifier Splitting Improve Open-Vocabulary Language Model of Code?
Jieke Shi, Zhou Yang, Junda He +2
Statistical language models on source code have successfully assisted software engineering tasks. However, developers can create or pick arbitrary identifiers when writing source c…
Revisiting Neuron Coverage Metrics and Quality of Deep Neural Networks
Zhou Yang, Jieke Shi, Muhammad Hilmi Asyrofi +1
Deep neural networks (DNN) have been widely applied in modern life, including critical domains like autonomous driving, making it essential to ensure the reliability and robustness…