Search Results for author:
Found 10 papers, 7 papers with code
AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
Particularly, abundant grammar tokens and formatting tokens are included to make the code more readable to humans.
Reversible Jump Attack to Textual Classifiers with Modification Reduction
Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models.
When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code.
CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models
Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages.
Source Code Data Augmentation for Deep Learning: A Survey
This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field.
Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process
In response, this study proposes a new method called the Fraud's Bargain Attack (FBA), which uses a randomization mechanism to expand the search space and produce high-quality adversarial examples with a higher probability of success.
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
The experimental results show that the proposed estimator helps save 23. 3% of computational cost measured in floating-point operations for the code completion systems, and 80. 2% of rejected prompts lead to unhelpful completion
On the Importance of Building High-quality Training Datasets for Neural Code Search
The performance of neural code search is significantly influenced by the quality of the training data from which the neural models are derived.
CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning
Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community.
Req2Lib: A Semantic Neural Model for Software Library Recommendation
In this work, we would like to make recommendations based on requirement descriptions to avoid these problems.
