SnT, University of Luxembourg


Welcome to TOOS!

TruX Open Online Seminars serve as a vibrant platform where researchers gather to discuss the latest advancements in software security, software repair, and cutting-edge explainable software techniques.

These sessions offer a valuable opportunity for young researchers to share their findings and engage in insightful discussions. Covering a wide range of software-related topics, these seminars provide an important space for experts and enthusiasts to explore new trends, exchange ideas, and create innovative solutions. By bringing together diverse perspectives, these seminars significantly contribute to shaping the future of software technologies, making them more dependable, robust, and effective.



Prof. Dr. Tegawendé Bissyandé

Prof. Dr. Jacques Klein

Upcoming Seminars

Aashish Yadavally

UT Dallas

Contextuality of Code Representation Learning

Advanced machine learning models (ML) have been successfully leveraged in several software engineering (SE) applications. The existing SE techniques have used the embedding models ranging from static to contextualized ones to build the vectors for program units. The contextualized vectors address a phenomenon in natural language texts called polysemy, which is the coexistence of different meanings of a word/phrase. However, due to different nature, program units exhibit the nature of mixed polysemy. Some code tokens and statements exhibit polysemy while other tokens (e.g., keywords, separators, and operators) and statements maintain the same meaning in different contexts. A natural question is whether static or contextualized embeddings fit better with the nature of mixed polysemy in source code. The answer to this question is helpful for the SE researchers in selecting the right embedding model. We conducted experiments on 12 popular sequence-/tree-/graph-based embedding models and on the samples of a dataset of 10,222 Java projects with +14M methods. We present several contextuality evaluation metrics adapted from natural-language texts to code structures to evaluate the embeddings from those models. Among several findings, we found that the models with higher contextuality help a bug detection model perform better than the static ones. Neither static nor contextualized embedding models fit well with the mixed polysemy nature of source code. Thus, we develop Hycode, a hybrid embedding model that fits better with the nature of mixed polysemy in source code.

Presentation Date: Monday, January 15, 2024 at 3:00 PM CET

Xin-Cheng Wen


When Less is Enough: Positive and Unlabeled Learning Model for Vulnerability Detection

Automated code vulnerability detection has gained increasing attention in recent years. The deep learning (DL)-based methods, which implicitly learn vulnerable code patterns, have proven effective in vulnerability detection. The performance of DL-based methods usually relies on the quantity and quality of labeled data. However, the current labeled data are generally automatically collected, such as crawled from human-generated commits, making it hard to ensure the quality of the labels. Prior studies have demonstrated that the non-vulnerable code (i.e., negative labels) tends to be unreliable in commonly-used datasets, while vulnerable code (i.e., positive labels) is more determined. Considering the large numbers of unlabeled data in practice, it is necessary and worth exploring to leverage the positive data and large numbers of unlabeled data for more accurate vulnerability detection. In this paper, we focus on the Positive and Unlabeled (PU) learning problem for vulnerability detection and propose a novel model named PILOT, i.e., Positive and unlabeled Learning mOdel for vulnerability deTection. PILOT only learns from positive and unlabeled data for vulnerability detection. It mainly contains two modules: (1) A distance-aware label selection module, aiming at generating pseudo-labels for selected unlabeled data, which involves the inter-class distance prototype and progressive fine-tuning; (2) A mixed-supervision representation learning module to further alleviate the influence of noise and enhance the discrimination of representations. The experimental results show that PILOT outperforms the popular weakly supervised methods by 2.78%-18.93% in the PU learning setting. Compared with the state-of-the-art methods, PILOT also improves the performance of 1.34%-12.46 % in F1 score metrics in the supervised setting. In addition, PILOT can identify 23 mislabeled from the FFMPeg+Qemu dataset in the PU learning setting based on manual checking.

Presentation Date: Monday, January 29, 2024 at 10:30 AM CET

Past Seminars

  • Robust Learning from Noisy and Imbalanced Software Engineering Datasets, Monday, December 4, 2023, by Zhong Li from NJU
    Zhong Li

    Nanjing University

    Robust Learning of Deep Predictive Models from Noisy and Imbalanced Software Engineering Datasets

    With the rapid development of Deep Learning, deep predictive models have been widely applied to improve Software Engineering tasks, such as defect prediction and issue classification, and have achieved remarkable success. They are mostly trained in a supervised manner, which heavily relies on high-quality datasets. Unfortunately, due to the nature and source of software engineering data, the real-world datasets often suffer from the issues of sample mislabelling and class imbalance, thus undermining the effectiveness of deep predictive models in practice. This problem has become a major obstacle for deep learning-based Software Engineering. In this paper, we propose RobustTrainer, the first approach to learning deep predictive models on raw training datasets where the mislabelled samples and the imbalanced classes coexist. RobustTrainer consists of a two-stage training scheme, where the first learns feature representations robust to sample mislabelling and the second builds a classifier robust to class imbalance based on the learned representations in the first stage. We apply RobustTrainer to two popular Software Engineering tasks, i.e., Bug Report Classification and Software Defect Prediction. Evaluation results show that RobustTrainer effectively tackles the mislabelling and class imbalance issues and produces significantly better deep predictive models compared to the other six comparison approaches.

    Presentation Date: Monday, December 18, 2023 at 10:30 AM CET

  • Dataflow Analysis-Inspired DL for Efficient Vulnerability Detection, Monday, December 4, 2023, by Benjamin Steenhoek from ISU
    Benjamin Steenhoek

    Iowa State University

    Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection

    Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing approaches use token-based transformer models, which are not the most efficient to capture code semantics required for vulnerability detection. In this paper, we propose to combine such causal-based vulnerability detection algorithms with deep learning, aiming to achieve more efficient and effective vulnerability detection. Specifically, we designed DeepDFA, a dataflow analysis-inspired graph learning framework and an embedding technique that enables graph learning to simulate dataflow computation. We show that DeepDFA is both performant and efficient. DeepDFA outperformed all non-transformer baselines. It was trained in 9 minutes, 75x faster than the highest-performing baseline model. When using only 50+ vulnerable and several hundreds of total examples as training data, the model retained the same performance as 100% of the dataset. DeepDFA also generalized to real-world vulnerabilities in DbgBench; it detected 8.7 out of 17 vulnerabilities on average across folds and was able to distinguish between patched and buggy versions. By combining DeepDFA with a large language model, we surpassed the state-of-the-art vulnerability detection performance on the Big-Vul dataset with 96.46 F1 score, 97.82 precision, and 95.14 recall.

    Presentation Date: Monday, December 4, 2023 at 3:00 PM CET

  • Towards Understanding Fairness and its Composition in Ensemble ML, Monday, November 20, 2023, by Usman Gohar from ISU
    Usman Gohar

    Iowa State University

    Towards Understanding Fairness and its Composition in Ensemble Machine Learning

    Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc. Many recent works have proposed methods to measure and mitigate algorithmic bias in ML models. The existing approaches focus on single classifier-based ML models. However, real-world ML models are often composed of multiple independent or dependent learners in an ensemble (e.g., Random Forest), where the fairness composes in a non-trivial way. How does fairness compose in ensembles? What are the fairness impacts of the learners on the ultimate fairness of the ensemble? Can fair learners result in an unfair ensemble? Furthermore, studies have shown that hyperparameters influence the fairness of ML models. Ensemble hyperparameters are more complex since they affect how learners are combined in different categories of ensembles. In this paper, we comprehensively study popular real-world ensembles: Bagging, Boosting, Stacking, and Voting. We have developed a benchmark of 168 ensemble models collected from Kaggle on four popular fairness datasets. We use existing fairness metrics to understand the composition of fairness. Our results show that ensembles can be designed to be fairer without using mitigation techniques. We also identify the interplay between fairness composition and data characteristics to guide fair ensemble design.

    Presentation Date: Monday, November 20, 2023 at 4:00 PM CET

  • ITER: Iterative Neural Repair for Multi-Location Patches, Monday, November 6, 2023, by He Ye from CMU
    He Ye

    Carnegie Mellon University

    ITER: Iterative Neural Repair for Multi-Location Patches

    Automated program repair (APR) has achieved promising results, especially using neural networks. Yet, the overwhelming majority of patches produced by APR tools are confined to one single location. When looking at the patches produced with neural repair, most of them fail to compile, while a few uncompilable ones go in the right direction. In both cases, the fundamental problem is to ignore the potential of partial patches. In this paper, we propose an iterative program repair paradigm called ITER founded on the concept of improving partial patches until they become plausible and correct. First, ITER iteratively improves partial single-location patches by fixing compilation errors and further refining the previously generated code. Second, ITER iteratively improves partial patches to construct multi-location patches, with fault localization re-execution. ITER is implemented for Java based on battle-proven deep neural networks and code representation. ITER is evaluated on 476 bugs from 10 open-source projects in Defects4J 2.0. ITER succeeds in repairing 76 of them, including 15 multi-location bugs which is a new frontier in the field.

    Presentation Date: Monday, November 6, 2023 at 3:00 PM CET

  • Guided Malware Sample Analysis Based on Graph Neural Networks, Monday, October 30, 2023, by Yi-Hsien Chen from NTU
    Yi-Hsien Chen

    National Taiwan University

    Guided Malware Sample Analysis Based on Graph Neural Networks

    Malicious binaries have caused data and monetary loss to people, and these binaries keep evolving rapidly nowadays. While manual analysis is slow and ineffective, automated malware report generation is a long-term goal for malware analysts and researchers. This study moves one step toward the goal by identifying essential functions in malicious binaries to accelerate and even automate the analyzing process. We design and implement an expert system based on our proposed graph neural network called MalwareExpert. The system pinpoints the essential functions of an analyzed sample and visualizes the relationships between involved parts. The evaluation results show that our approach has a competitive detection performance (97.3% accuracy and 96.5% recall rate) compared to existing malware detection models. Moreover, it gives an intuitive and easy-to-understand explanation of the model predictions by visualizing and correlating essential functions. We compare the identified essential functions reported by our system against several expert-made malware analysis reports from multiple sources. Our qualitative and quantitative analyses show that the pinpointed functions indicate accurate directions. In the best case, the top 2% of functions reported from the system can cover all expert-annotated functions in three steps. We believe that the MalwareExpert system has shed light on automated program behavior analysis.

    Presentation Date: Monday, October 30, 2023 at 10:30 AM CET

  • Rete: Learning Namespace Representation for Program Repair, Monday, October 9, 2023, by Nikhil Parasaram from UCL
    Nikhil Parasaram

    University College London

    Rete: Learning Namespace Representation for Program Repair

    A key challenge of automated program repair is finding correct patches in the vast search space of candidate patches. Real-world programs define large namespaces of variables that considerably contributes to the search space explosion. Existing program repair approaches neglect information about the program namespace, which makes them inefficient and increases the chance of test-overfitting. We propose Rete, a new program repair technique, that learns project-independent information about program namespace and uses it to navigate the search space of patches. Rete uses a neural network to extract project-independent information about variable CDU chains, def-use chains augmented with control flow. Then, it ranks patches by jointly ranking variables and the patch templates into which the variables are inserted. We evaluated Rete on 142 bugs extracted from two datasets, ManyBugs and BugsInPy. Our experiments demonstrate that Rete generates six new correct patches that fix bugs that previous tools did not repair, an improvement of 31% and 59% over the existing state of the art.

    Presentation Date: Monday, October 9, 2023 at 10:30 AM CEST