High-precision static analysis can effectively detect Null Pointer Dereference (NPD) vulnerabilities in C language, but the performance overhead is significant. In recent years, researchers have attempted to enhance the efficiency of static analysis by leveraging multicore resources. However, due to complex dependencies in the analysis process, the parallelization of static value-flow NPD analysis for large-scale software still faces significant challenges. It is difficult to achieve a good balance between detection efficiency and accuracy, which impacts its application.This paper presents PANDA, the first parallel detector for high-precision static value-flow NPD analyzer in the C language. The core idea of PANDA is to utilize dependency analysis to ensure high precision while decoupling the strong dependencies between static value-flow analysis steps. This transforms the traditionally challenging-to-parallelize NPD analysis into two parallelizable algorithms: function summarization and combined query-based vulnerability analysis. PANDA introduces a task-level parallel framework and enhances it with a dynamic scheduling method to parallel schedule the above two key steps, significantly improving the performance and scalability of memory vulnerability detection.Fully implemented within the LLVM framework (version 15.0.7), PANDA demonstrates a significant advantage in balancing accuracy and efficiency compared to current popular open-source detection tools. In precision-targeted benchmark tests, PANDA maintains a false positive rate within 3.17% and a false negative rate within 5.16%; in historical CVE detection rate tests, its recall rate far exceeds that of comparative open-source tools. In performance evaluations, compared to its serial version, PANDA achieves up to an 11.23-fold speedup on a 16-node server, exhibiting outstanding scalability.

Taint analysis of value flows, as a static analysis technique, has gained widespread application in the fields of software security and vulnerability mining. However, when dealing with complex programs, it still faces challenges in terms of precision and performance. This research proposes P-DATA, a parallel framework implementing dependency-aware taint analysis. P-DATA employs modeling to capture data and control dependencies, reducing false positives over tools like Clang Static Analyzer and SVF. To accelerate the analysis, P-DATA leverages a task-level parallel framework introducing Preemption of Computational Resources (PCR) and Asynchronous Taint Source Registration, lead to impressive scalability and efficiency. Evaluations demonstrate P-DATA's ability to significantly expedite taint analysis for large programs using multi-core resources, achieving over 25X speedup on 32 cores. P-DATA makes notable contributions by boosting precision, efficiency and scalability of security-critical program analysis through advanced dependency modeling and paral-lelization techniques. It provides an extensible high-performance framework benefiting static analysis advancement.

Memory vulnerability detection aims to identify software defects that can compromise memory safety. However, existing methods often struggle to achieve both high precision and efficiency. This paper presents a high-precision memory vulnerability detection approach based on value flow analysis and parallel computing. We first construct a static semantic representation called SVFG to enable precise detection of memory vulnerabilities such as null pointer dereference and use-after-free. We then perform dependency-aware path feasibility analysis using an SMT solver to reduce false positives. Finally, we develop a task-level parallel framework to accelerate the constraint solving process and improve efficiency.We evaluate our approach on the Juliet test set of over 2,000 test cases and 7 open-source projects. Experimental results show that our dependency-aware analysis can achieve 0.5%-2.05% false positive rates, outperforming traditional approaches and existing tools. Our task-level parallel framework can achieve up to 3.25x speedup with 4 computing nodes.Our study demonstrates that combining value flow analysis and parallel computing is a promising way to enable highly precise and efficient detection of memory vulnerabilities. For future work, we plan to integrate pointer analysis to support more complex codes, and optimize the granularity of parallelism to improve scalability. Overall, this paper presents a static analysis based method to address the inherent trade-off between precision and efficiency in memory vulnerability detection.