Xiao Cheng

Xiao Cheng

Auto-generated profile, based on publicly available information

Xiao Cheng

Macquarie University, Sydney, Australia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2022 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
XCXiao Cheng
Xiao Cheng
XNXu Nie
Xu Nie
NLNingke Li
Ningke Li
HWHaoyu Wang
Haoyu Wang
ZZZheng Zheng
Zheng Zheng
YSYulei Sui
Yulei Sui
Machine learning and its promising branch deep learning have proven to be effective in a wide range of application domains. Recently, several efforts have shown success in applying deep learning techniques for automatic vulnerability discovery, as alternatives to traditional static bug detection. In principle, these learning-based approaches are built on top of classification models using supervised learning. Depending on the different granularities to detect vulnerabilities, these approaches rely on learning models which are typically trained with well-labeled source code to predict whether a program method, a program slice, or a particular code line contains a vulnerability or not. The effectiveness of these models is normally evaluated against conventional metrics including precision, recall and F1 score. In this paper, we show that despite yielding promising numbers, the above evaluation strategy can be insufficient and even misleading when evaluating the effectiveness of current learning-based approaches. This is because the underlying learning models only produce the classification results or report individual/isolated program statements, but are unable to pinpoint bug-triggering paths, which is an effective way for bug fixing and the main aim of static bug detection. Our key insight is that a program method or statement can only be stated as vulnerable in the context of a bug-triggering path. In this work, we systematically study the gap between recent learning-based approaches and conventional static bug detectors in terms of fine-grained metrics called BTP metrics using bug-triggering paths. We then characterize and compare the quality of the prediction results of existing learning-based detectors under different granularities. Finally, our comprehensive empirical study reveals several key issues and challenges in developing classification models to pinpoint bug-triggering paths and calls for more advanced learning-based bug detection techniques.

12 July 2024 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
XCXiao Cheng
Xiao Cheng
JRJiawei Ren
Jiawei Ren
YSYulei Sui
Yulei Sui
Typestate analysis is a commonly used static technique to identify software vulnerabilities by assessing if a sequence of operations violates temporal safety specifications defined by a finite state automaton. Path sensitive typestate analysis (PSTA) offers a more precise solution by eliminating false alarms stemming from infeasible paths. To improve the efficiency of path-sensitive analysis, previous efforts have incorporated sparse techniques, with a focus on analyzing the path feasibility of def-use chains. However, they cannot be directly applied to detect typestate vulnerabilities requiring temporal information within the control flow graph like use-to-use information. In this paper, we introduce FGS, a F ast G raph S implification approach designed for PSTA by retaining multi-point temporal information while harnessing the advantages of sparse analysis. We propose a new multi-point slicing technique that captures the temporal and spatial correlations within the program. By doing so, it optimizes the program by only preserving the necessary program dependencies, resulting in a sparser structure for precision-preserving PSTA. Our graph simplification approach, as a fast preprocessing step, offers several benefits for existing PSTA algorithms. These include a more concise yet precision-preserving graph structure, decreased numbers of variables and constraints within execution states, and simplified path feasibility checking. As a result, the overall efficiency of the PSTA algorithm exhibits significant improvement. We evaluated FGS using NIST benchmarks and ten real-world large-scale projects to detect four types of vulnerabilities, including memory leaks, double-frees, use-after-frees, and null dereferences. On average, when comparing FGS against ESP (baseline PSTA), FGS reduces 89% of nodes, 86% of edges, and 88% of calling context of the input graphs, obtaining a speedup of 116× and a memory usage reduction of 93% on the large projects evaluated. Our experimental results also demonstrate that FGS outperforms six open-source tools (IKOS, ClangSA, Saber, Cppcheck, Infer , and Sparrow ) on the NIST benchmarks, which comprises 846 programs. Specifically, FGS achieves significantly higher precision, with improvements of up to 171% (42% on average), and detects a greater number of true positives, with enhancements of up to 245% (52% on average). Moreover, among the ten large-scale projects, FGS successfully found 105 real bugs with a precision rate of 82%. In contrast, our baseline tools not only missed over 42% of the real bugs but also yielded an average precision rate of just 13%.

12 April 2024
Verified
Conference Paper
Open access
XCXiao Cheng
Xiao Cheng
JWJiawei Wang
Jiawei Wang
YSYulei Sui
Yulei Sui
Sparse static analysis offers a more scalable solution compared to its non-sparse counterpart. The basic idea is to first conduct a fast pointer analysis that over-approximates the value-flows and propagates the data-flow facts sparsely along only the pre-computed value-flows instead of all control flow points. Current sparse techniques focus on improving the scalability of the main analysis while maintaining its precision. However, their pointer analyses in both the offline and main phases are inherently imprecise because they rely solely on a single memory address domain without considering values from other domains like the interval domain. Consequently, this leads to conservative alias results, like arrayinsensitivity, which leaves substantial room for precision improvement of the main data-flow analysis. This paper presents CSA, a new Cross-domain Sparse Abstract execution that interweaves correlations between values across multiple abstract domains (e.g., memory address and interval domains). Unlike traditional sparse analysis without cross-domain interaction, CSA performs correlation tracking by establishing implications of values from one domain to another. This correlation tracking enables online bidirectional refinement: CSA refines spurious alias relations using interval domain information and also enhances the precision of interval analysis with refined alias results. This contributes to increasingly improved precision and scalability as the main analysis progresses. To improve the efficiency of correlation tracking, we propose an equivalent correlation tracking approach that groups (virtual) memory addresses with equivalent implication results to minimize redundant value joins and storage associated. We apply CSA on two common assertion-based checking clients, buffer overflow and null dereference detection. Experimental results show that CSA outperforms five open-source tools (Infer, Cppcheck, IKOS, Sparrow and KLEE) on ten large-scale projects. CSA finds 111 real bugs with 68.51% precision, detecting 46.05% more bugs than Infer and exhibiting 12.11% more precision rate than KLEE. CSA records 96.63% less false positives on real-world projects than the version without cross-domain interaction. CSA also exhibits an average speedup of 2.47× and an average memory reduction of 6.14× with equivalent correlation tracking.

19 June 2025 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
HLHaodong Li
Haodong Li
XCXiao Cheng
Xiao Cheng
GZGuohan Zhang
Guohan Zhang
GXGuosheng Xu
Guosheng Xu
GXGuoai Xu
Guoai Xu
HWHaoyu Wang
Haoyu Wang
Learning-based Android malware detection has earned significant recognition across industry and academia, yet its effectiveness hinges on the accuracy of labeled training data. Manual labeling, being prohibitively expensive, has prompted the use of automated methods, such as leveraging anti-virus engines like VirusTotal, which unfortunately introduces mislabeling, aka "label noise". The state-of-the-art label noise reduction approach, MalWhiteout, can effectively reduce random label noise but underperforms in mitigating real-world emergent malware (EM) label noise stemming from newly emerging Android malware variants overlooked by VirusTotal. To tackle this, we conceptualize EM label noise detection as an anomaly detection problem and introduce a novel tool, MalCleanse, that surpasses MalWhiteout's ability to address EM label noise. MalCleanse combines uncertainty estimation with unsupervised anomaly detection, identifying samples with high uncertainty as mislabeled, thereby enhancing its capability to remove EM label noise. Our experimental results demonstrate a significant reduction in EM label noise by approximately 25.25%, achieving an F1 Score of 80.32% for label noise detection at a noise ratio of 40.61%. Notably, MalCleanse outperforms MalWhiteout with an increase of 40.9% in overall F1 score for mitigating EM label noise. This paper pioneers the integration of deep neural network model uncertainty to refine label accuracy, thereby enhancing the reliability of malware detection systems. Our approach represents a significant step forward in addressing the challenges posed by emergent malware in automated labeling systems.

22 June 2025 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
HLHaodong Li
Haodong Li
XCXiao Cheng
Xiao Cheng
YZYanjie Zhao
Yanjie Zhao
GXGuosheng Xu
Guosheng Xu
GXGuoai Xu
Guoai Xu
HWHaoyu Wang
Haoyu Wang
Android malware detection remains a critical challenge in cybersecurity research. Recent advancements leverage AI techniques, particularly deep neural networks (DNNs), to train a detection model, but their effectiveness is often compromised by the pronounced imbalance among malware families in commonly used training datasets. This imbalance leads to overfitting in dominant categories and poor performance in underrepresented ones, increasing predictive uncertainty for less common malware families. To address the suboptimal performance of many DNN models, we introduce MalTutor, a novel framework that enhances model robustness through an optimized training process. Our primary insight lies in transforming uncertainties from “liabilities” into “assets” by strategically incorporating them into DNN training methodologies. Specifically, we begin by evaluating the predictive uncertainty of DNN models throughout various training epochs, which guides our sample categorization. Incorporating Curriculum Learning strategies, we commence training with easy-to-learn samples with lower uncertainty, progressively incorporating difficult-to-learn ones with higher uncertainty. Our experimental results demonstrate that MalTutor significantly improves the performance of models trained on imbalanced datasets, increasing accuracy by 31.0%, elevating the F1 score by 138.8%, and specifically boosting the average accuracy in detecting various types of malicious apps by 133.9%. Our findings provide valuable insights into the potential benefits of incorporating uncertainty to improve the robustness of DNN models for prediction-oriented software engineering tasks.

4 June 2024 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
JRJiawei Ren
Jiawei Ren
YSYulei Sui
Yulei Sui
XCXiao Cheng
Xiao Cheng
YFYuan Feng
Yuan Feng
JZJianjun Zhao
Jianjun Zhao
Many existing static analysis algorithms suffer from cubic bottlenecks because of the need to compute a dynamic transitive closure (DTC). For the first time, this article studies the quantum speedups on searching subtasks in DTC-based static analysis algorithms using quantum search (e.g., Grover’s algorithm). We first introduce our oracle implementation in Grover’s algorithm for DTC-based static analysis and illustrate our quantum search subroutine. Then, we take two typical DTC-based analysis algorithms: context-free-language reachability and set constraint-based analysis, and show that our quantum approach can reduce the time complexity of these two algorithms to truly subcubic ( \(O(N^2\sqrt {N}{\it polylog}(N))\) ), yielding better results than the upper bound ( O ( N 3 /log N )) of existing classical algorithms. Finally, we conducted a classical simulation of Grover’s search to validate our theoretical approach, due to the current quantum hardware limitation of lacking a practical, large-scale, noise-free quantum machine. We evaluated the correctness and efficiency of our approach using IBM Qiskit on nine open-source projects and randomly generated edge-labeled graphs/constraints. The results demonstrate the effectiveness of our approach and shed light on the promising direction of applying quantum algorithms to address the general challenges in static analysis.