Search Results for author:
Found 22 papers, 12 papers with code
Importance Guided Data Augmentation for Neural-Based Code Understanding
In this paper, we introduce a general data augmentation framework, GenCode, to enhance the training of code understanding models.
Hazards in Deep Learning Testing: Prevalence, Impact and Recommendations
To this end, we survey the related literature and identify 10 commonly adopted empirical evaluation hazards that may significantly impact experimental results.
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.
Boosting Source Code Learning with Data Augmentation: An Empirical Study
The next era of program understanding is being propelled by the use of machine learning to solve software problems.
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models.
MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation
Data augmentation has been a popular approach to supplement training data in domains such as computer vision and NLP.
On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing
Graph neural network (GNN)-based graph learning has been popular in natural language and programming language processing, particularly in text and source code classification.
LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks.
Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation
Recent studies show that test selection for DNN is a promising direction that tackles this issue by selecting minimal representative data to label and using these data to assess the model.
CodeS: Towards Code Model Generalization Under Distribution Shift
Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation.
LaF: Labeling-Free Model Selection for Automated Deep Neural Network Reusing
Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem.
Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment
The results reveal that 1) data with distribution shifts happen more disagreements than without.
Robust Active Learning: Sample-Efficient Training of Robust Deep Learning Models
Our acquisition function -- named density-based robust sampling with entropy (DRE) -- outperforms the other acquisition functions (including random) in terms of robustness by up to 24. 40\% (3. 84\% than random particularly), while remaining competitive on accuracy.
Adversarial Robustness in Multi-Task Learning: Promises and Illusions
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks.
Learning from What We Know: How to Perform Vulnerability Prediction using Noisy Historical Data
To tackle these issues, we propose TROVON, a technique that learns from known vulnerable components rather than from vulnerable and non-vulnerable components, as typically performed.
Machine Translation
Cryptography and Security
Software Engineering
Influence-Driven Data Poisoning in Graph-Based Semi-Supervised Classifiers
Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data.
IBIR: Bug Report driven Fault Injection
It remains indeed challenging to inject few but realistic faults that target a particular functionality in a program.
Fault Detection
Program Repair
+2
Software Engineering
Efficient and Transferable Adversarial Examples from Bayesian Neural Networks
An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity.
Adversarial Embedding: A robust and elusive Steganography and Watermarking technique
The key idea of our method is to use deep neural networks for image classification and adversarial attacks to embed secret information within images.
Test Selection for Deep Learning Systems
This raises the question of how we can automatically select candidate test data to test deep learning models.
Automated Search for Configurations of Deep Neural Network Architectures
First, we model the variability of DNN architectures with a Feature Model (FM) that generalizes over existing architectures.
Assessing and Improving the Mutation Testing Practice of PIT
We therefore examine how effective are the mutants of a popular mutation testing tool, named PIT, compared to comprehensive ones, as drawn from the literature and personal experience.
Software Engineering
