tianzhaotju / CODA
We propose a novel adversarial example generation technique (i.e., CODA) for testing deep code models. Its key idea is to use code differences between the target input and reference inputs to guide the generation of adversarial examples.
☆13Updated last year
Related projects ⓘ
Alternatives and complementary repositories for CODA
- Towards Robustness of Deep Program Processing Models – Detection, Estimation and Enhancement☆19Updated 2 years ago
- ☆11Updated last year
- ☆40Updated last year
- [SANER 2023] MixCode: Enhancing Code Classification by Mixup-Based Data Augmentation☆13Updated 3 months ago
- ☆12Updated 2 years ago
- ☆33Updated 2 years ago
- ☆10Updated last year
- ☆10Updated 2 years ago
- This repo illustrates how to evaluate the artifacts in the paper An Extensive Study on Pre-trained Models for Program Understanding and G…☆25Updated 2 years ago
- Replication Package for "Natural Attack for Pre-trained Models of Code", ICSE 2022☆41Updated 2 months ago
- This repo illustrates how to evaluate the artifacts in the paper Deep Just-in-Time Defect Prediction: How Far Are We? published in ISSTA'…☆36Updated 11 months ago
- For our ICSE 2023 paper KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair☆30Updated last year
- NLQF is a tool to filter query-appropriate comments for building high-quality code search datasets.☆17Updated 2 years ago
- ☆10Updated last year
- IST'21 & SANER'22: Semantic-Preserving Program Transformations☆31Updated 2 years ago
- ☆19Updated 4 years ago
- ☆13Updated last year
- ☆13Updated 2 years ago
- When Less is Enough: Positive-Unlabeled Learning Model for Vulnerability Detection☆11Updated 10 months ago
- this is the repository for the paper titled "The Best of Both Worlds: Integrating Semantic Features with Expert Features for Defect Predi…☆15Updated last year
- ☆14Updated 2 years ago
- ☆49Updated 3 years ago
- ☆11Updated 8 months ago
- Neural Program Repair with Execution-based Backpropagation http://arxiv.org/pdf/2105.04123☆24Updated last year
- ☆35Updated last year
- We propose a novel DL-based mutation technique (LEAM), which adapts the syntax-guided encoder-decoder architecture to build two sub-model…☆27Updated 4 months ago
- Enhacing Code Pre-trained Models by Contrastive Learning☆29Updated last year
- Automated Classification of Overfitting Patches with Statically Extracted Code Features http://arxiv.org/pdf/1910.12057☆10Updated last year
- Program Transformation Tool for Java Methods☆11Updated 2 years ago
- This repository is the replication package of the ICSE22 paper "FIRA: Fine-Grained Graph-Based Code Change Representation for Automated C…☆31Updated 2 years ago