Vulnerability-Fixing Commit Identification(VFCI) is a critical task in software security maintenance that aims to automatically identify code commits that patch security vulnerabilities. However, existing approaches face challenges in handling low-quality commit messages and entangled commits, which limit their identification performance. To address these issues, we propose VFCionX, a novel VFCI framework that integrates large and small language models in a collaborative architecture. VFCionX consists of three core modules: Message Classifier, Patch Classifier, and Ensemble Classifier. The Message Classifier employs a multi-source contextual augmentation strategy to enhance the quality of commit messages and fine-tunes the Qwen2.5-1.5B model, significantly improving classification performance in the textual modality. The Patch Classifier combines heuristic rules with a Qwen2.5-Coder-7B-driven file selector to filter noise from entangled commits, and incorporates a line-level feature extractor based on CodeBERT and CNN to capture local pattern differences between added and deleted code lines. The Ensemble Classifier integrates predictions from both channels using the AdaBoost algorithm, enhancing model robustness and generalization. Experimental results on five popular C/C++ repositories comprising 24,630 commits show that VFCionX achieves an F1-score of 81.47%, outperforming the best baseline by 9.42%. Ablation studies validate the effectiveness of each component, while sensitivity analysis reveals optimal parameter settings for balancing performance and noise resilience. This work provides a new and effective solution for robust vulnerability patch identification.

The Instruction Set Architecture (ISA) defines processor operations and serves as the interface between hardware and software. As an open ISA, RISC-V lowers the barriers to processor design and encourages widespread adoption, but also exposes processors to security risks such as functional bugs. Processor fuzzing is a powerful technique for automatically detecting these bugs. However, existing fuzzing methods suffer from two main limitations. First, their emphasis on redundant test case generation causes them to overlook cross-processor corner cases. Second, they rely too heavily on coverage guidance. Current coverage metrics are biased and inefficient, and become ineffective once coverage growth plateaus.To overcome these limitations, we propose SimFuzz, a fuzzing framework that constructs a high-quality seed corpus from historical bug-triggering inputs and employs similarity-guided, block-level mutation to efficiently explore the processor input space. By introducing instruction similarity, SimFuzz expands the input space around seeds while preserving control-flow structure, enabling deeper exploration without relying on coverage feedback. We evaluate SimFuzz on three widely used open-source RISC-V processors: Rocket, BOOM, and XiangShan, and discover 17 bugs in total, including 14 previously unknown issues, 7 of which have been assigned CVE identifiers. These bugs affect the decode and memory units, cause instruction and data errors, and can lead to kernel instability or system crashes. Experimental results show that SimFuzz achieves up to 73.22% multiplexer coverage on the high-quality seed corpus. Our findings highlight critical security bugs in mainstream RISC-V processors and offer actionable insights for improving functional verification.

To mitigate the security and compliance risks posed by Android third-party libraries (TPLs), researchers have proposed many automated detection tools aimed at accurately identifying TPLs within Android applications (apps). The detection results serve as the foundation for practical downstream tasks such as software bill of materials (SBOM) generation, n-day vulnerability identification, compliance auditing, and software supply chain risk tracing, among others. However, despite the high levels of detection accuracy and efficiency achieved by state-of-the-art TPL detection tools, existing studies lack a systematic evaluation of these tools' robustness against potential malicious attacks. As a result, the risk of detection failure in real-world scenarios remains unmanageable. Tools with poor robustness may be rendered ineffective under attack, allowing unsafe and non-compliant TPLs within apps to evade scrutiny and analysis, thereby compromising user interests. To bridge this gap, we propose the first adversarial attack against TPL detection tools,LibPass. The core idea ofLibPassis to generate adversarial apps by crafting perturbations that go beyond the code transformations introduced by obfuscation techniques. These adversarial perturbations hinder the generalization capability of existing detection tools, which are primarily designed to counter code obfuscation, thereby enabling the evasion of TPL detection. To minimize attack overhead and enhance stealthiness,LibPassemploys an improved firefly algorithm to search for optimal adversarial apps. This work evaluates the effectiveness ofLibPassagainst five state-of-the-art TPL detection tools on three datasets of different types and benchmarks its performance against three baseline attack methods. Experimental results demonstrate thatLibPassachieves an average attack success rate of 61.33%, with a peak of 99.46%, underscoring the insufficient robustness of current TPL detection tools.

Software repositories such as PyPI and npm are vital for software development but expose users to serious security risks from malicious packages. The malicious packages often execute their payloads immediately upon installation, leading to rapid system compromise. Existing detection methods are heavily dependent on difficult-to-obtain explicit knowledge, rendering them susceptible to overlooking emergent malicious packages.In this paper, we present a lightweight and effective method, namely EMPHunter, to detect malicious packages without requiring any explicit prior knowledge. EMPHunter is founded upon two fundamental and insightful observations. First, malicious packages are considerably rarer than benign ones, and second, the functionality of installation scripts for malicious packages diverges significantly from those of benign packages, with the latter frequently forming clusters. Consequently, EMPHunter utilizes the clustering technique to group the unique installation scripts of new-uploaded packages and identifies outliers as candidate malicious packages. It then ranks the outliers according to their deviate degrees and the distance between each of them and known malicious instances, effectively highlighting potential malicious packages.With EMPHunter, we successfully identified 122 previously unknown malicious packages from a pool of 267,009 newly-uploaded PyPI and npm packages, achieving an mAP (Mean Average Precision) of 0.813 and an exceptional recall of 0.992 when auditing the top-10 rankings. All detected packages have been officially confirmed as genuine malicious package by PyPI and npm. We assert that EMPHunter offers a valuable and advantageous supplement to existing detection tools, augmenting the arsenal of software supply chain security analysis.

To facilitate understanding of users' diverse queries against the back-end databases in web applications, researchers have introduced Text-to-SQL (Text2SQL) models that can generate well-structured SQL queries from users' query texts in natural language. As the Text2SQL model decouples the user queries with the back-end databases, it inherently mitigates the SQL injection risk posed by inserting users' input into pre-written SQL queries. However, what security risks to web applications may be posed by Text2SQL models remains an open question. In this paper, we present a new attack framework, named Autoregression-based Injection Attacks (AIA), to evaluate the security risks of Text2SQL models. In particular, AIA makes target models generate attack payloads by constructing specific inputs and adjusting the input auto-regressively. Our evaluation demonstrates that AIA can cause Text2SQL models to generate target output by adversarial inputs with success rates of over 70% in most scenarios. The generated adversarial input has certain transferability in target Text2SQL models. Additionally, practice experiments show that AIA can make Text2SQL models extract user lists from databases and even delete data in databases directly.

Modern Python applications heavily rely on third-party libraries (TPLs), which can introduce security risks when vulnerabilities in these libraries silently propagate into client code. Determining whether a known vulnerability in a third-party library (TPL) can potentially be triggered in a specific downstream application is a key aspect of vulnerability reachability analysis, a research area that remains a manual, error-prone task due to the dynamic nature of the Python language and its implicit coding patterns. We present PyReach, a multi-agent collaborative framework that automates vulnerability reachability analysis for Python programs. Instead of statically resolving all dynamic behavior, PyReach decomposes the reasoning process into three semantically guided agents: 1) Context Modeling Agent that extracts auxiliary semantic context by analyzing and summarizing the semantic context of external dependencies for each function in a call chain; 2) Reachability Analysis Agent that determines whether a function in a call chain alters a vulner-ability’s triggering conditions by analyzing its inside semantics; 3) Reachability Verification Agent that determines if execution paths from user-facing entry points can reach the vulnerable code under the right conditions. We evaluate PyReach on a custom-built dataset, the largest of its kind for Python vulnerability reachability analysis, consisting of 15 real-world Python CVEs and 45 corresponding client projects. Experimental results show that PyReach achieves $90 \%$ precision and $83.3 \%$ specificity, significantly outperforming a call-graph-based baseline, Jarvis. PyReach effectively distinguishes between truly affected and unaffected clients by reasoning over code semantics and trigger profiles. Our results highlight the value of combining modular semantic reasoning with constraint propagation for accurate and scalable vulnerability analysis in dynamic languages.

Android applications (apps) integrate reusable and well-tested third-party libraries (TPLs) to enhance functionality and shorten development cycles. However, recent research reveals that TPLs have become the largest attack surface for Android apps, where the use of insecure TPLs can compromise both developer and user interests. To mitigate such threats, researchers have proposed various tools to detect TPLs used by apps, supporting further security analyses such as vulnerable TPLs identification. Although existing tools achieve notable library-level TPL detection performance in the presence of obfuscation, they struggle with version-level TPL detection due to a lack of sensitivity to differences between versions. This limitation results in a high version-level false positive rate, significantly increasing the manual workload for security analysts. To resolve this issue, we propose SAD, a TPL detection tool with high version-level detection performance. SAD generates a candidate app class list for each TPL class based on the feature of nodes in class dependency graphs (CDGs). It then identifies the unique corresponding app class for each TPL class by performing class matching based on the similarity of their class summaries. Finally, SAD identifies TPL versions by evaluating the structural similarity of the sub-graph formed by matched classes within the CDGs of the TPL and the app. Extensive evaluation on three datasets demonstrates the effectiveness of SAD and its components. SAD achieves F1 scores of 97.64% and 84.82% for library-level and version-level detection on obfuscated apps, respectively, surpassing existing state-of-the-art tools. The version-level false positives reported by the best tool is 1.61 times that of SAD. We further evaluate the degree to which TPLs identified by detection tools correspond to actual TPL classes. Experimental results show that SAD achieves a class-level F1 score of 94.12%, 11% higher than the best tool, demonstrating the reliability of SAD and better supporting downstream tasks that rely on specific code.

Background: In recent years, with the advancement of software engineering technologies and industry, Open Source Software (OSS) has become a mainstream model for software development and innovation. Increasingly, organizations and developers are adopting and customizing existing OSS to simplify and accelerate development processes. During OSS adoption, recommending suitable software based on user needs is crucial for enhancing development efficiency and addressing diverse requirements. However, the vast number and diversity of OSS make the recommendation task highly challenging. Despite progress in previous research, several issues remain, such as neglect of key software attributes, complexity in extracting multilingual features, and challenges of cold start and data sparsity. Aims: This paper presents AthenaRec, a large-scale OSS recommendation system comprising three core modules: Delphi, Argus, and Hestia. AthenaRec aims to recommend relevant and suitable software from a vast OSS based on user needs. Method: Specifically, Delphi first analyzes user queries to identify intention; Argus employs a heterogeneous ensemble recall approach to retrieve a large set of candidate software relevant to the identified intention; finally, Hestia adopts a two-stage deep ranking strategy. It performs coarse ranking by integrating multilingual modeling with contrastive learning, followed by fine ranking with a large language model, augmented by retrieval-augmented generation to incorporate external evidence. To evaluate the effectiveness of AthenaRec, we use a query dataset from real application scenarios. Results: Experimental results demonstrate that, on the test set of 7,500 queries, AthenaRec achieves superior recommendation performance, with Hits@20, MAP@20, NDCG@20, and MRR scores of$98.27 \%, 95.60 \%, 95.05 {\%}$, and 92.92%, respectively. On average, AthenaRec outperforms other top methods by 10.9% across all evaluation metrics. Conclusions: Additionally, we develop a Visual Studio Code (VSCode) plugin based on AthenaRec, which can be accessed via URL. We intend for this research to provide a reference for software developers, advancing the efficiency and accuracy of OSS recommendation.

The widespread application of large language models (LLMs) underscores the importance of deep learning (DL) technologies that rely on foundational DL libraries such as PyTorch and TensorFlow. Despite their robust features, these libraries face challenges with scalability and adaptation to rapid advancements in the LLM community. In response, tech giants like Apple and Huawei are developing their own DL libraries to enhance performance, increase scalability, and safeguard intellectual property. Ensuring the security of these libraries is crucial, with fuzzing being a vital solution. However, existing fuzzing frameworks struggle with target flexibility, effectively testing bug-prone API sequences, and leveraging the limited available information in new libraries. To address these limitations, we propose FUTURE, the first universal fuzzing framework tailored for newly introduced and prospective DL libraries. FUTURE leverages historical bug information from existing libraries and fine-tunes LLMs for specialized code generation. This strategy helps identify bugs in new libraries and uses insights from these libraries to enhance security in existing ones, creating a cycle from history to future and back. To evaluate FUTURE's effectiveness, we conduct comprehensive evaluations on three newly introduced DL libraries. Evaluation results demonstrate that FUTURE significantly outperforms existing fuzzers in bug detection, success rate of bug reproduction, validity rate of code generation, and API coverage. Notably, FUTURE has detected 148 bugs across 452 targeted APIs, including 142 previously unknown bugs. Among these, 10 have been assigned CVE IDs. Additionally, FUTURE detects 7 bugs in PyTorch, demonstrating its ability to enhance security in existing libraries in reverse.

Open Source Software (OSS) plays a vital role in modern software ecosystems, with README files providing essential information on functionality, configuration, and usage. However, approximately 9.03% of OSS projects lack adequate README documentation, impacting developer efficiency and software maintainability. Recent advances in natural language processing and large language models (LLMs) have automated README generation to reduce manual effort. Yet, existing methods struggle with integrating real-time external knowledge, parsing complex software structures, and adapting to projectspecific requirements. To address these challenges, this paper introduces RMGenie, a framework that leverages LLM-based agents and external tool invocation for automated README generation. RMGenie constructs an agent-driven workflow enabling multi-round interactions with external tools to dynamically extract critical code insights, particularly for complex software structures. It employs a Tree of Actions model with an entropy-based scoring mechanism to optimize decision paths for README generation. Additionally, a reflexion Mechanism enhances accuracy by mitigating decision biases and tool invocation errors. Experimental results confirm that RMGenie significantly outperforms baseline methods in content completeness, instruction adherence, and factual accuracy. Furthermore, we develop a plugin that integrates RMGenie to automatically generate README files from GitHub repositories, improving developer productivity and standardizing OSS documentation. The plugin is available at VSCode Marketplace.

Satisfiability Modulo Theory (SMT) solvers play a crucial role in various domains and applications. Therefore, ensuring their correctness and robustness becomes increasingly vital. Fuzzing is an efficient and effective method for validating the quality of SMT solvers, utilizing inputs that consist of solving formulas and configuration options. However, existing fuzzing methods focus solely on generating formulas or simply combining options and formulas, neglecting the complex interactions between options. Yet, randomly combining multiple options can lead to a combinatorial explosion and result in numerous invalid inputs. To overcome these limitations, we propose OptionFuzz, a fuzzer that optimizes option exploration by identifying relationships between solver options, reducing invalid inputs and mitigating combinatorial explosion. OptionFuzz identifies option relationships using large language models (LLMs), which analyze official documentation of options. These identified relationships are transformed to a relation graph, enabling efficient traversal to derive related option combinations and generate high-quality fuzz inputs. To evaluate OptionFuzz's effectiveness, we conduct comprehensive evaluations on two state-of-the-art SMT solvers, Z3 and CVC5. OptionFuzz demonstrates its effectiveness by accurately extracting option relationships with an accuracy of$\mathbf{9 5. 2 3 \%}$and a recall rate of$\mathbf{9 0. 1 0 \%}$. Leveraging these relationships, OptionFuzz reduces the number of options combinations to be tested by$\mathbf{7 0. 1 1 \%}$. Notably, OptionFuzz has detected$\mathbf{3 4}$unique bugs, 20 of which have been fixed by developers, and 5 have been assigned CVE IDs due to their severity.

Managing third-party libraries is a costly and critical task for enterprises, essential for both vulnerability assessment and license compliance. Existing android software composition analysis tools focus on mitigating code obfuscation but neglect the impact of code optimization, which is deeply integrated into build pipelines and disrupts library structure.To tackle these challenges, we developed LibSleuth, a detection tool designed to be resilient to code shrinking and obfuscation. It is based on the observation that even after shrinking, the remaining code still retains functional completeness. LibSleuth adopts two novel strategies: (1) Method level functional module matching: We break down feature matching to method level and define a functional module as related methods that represent used functionality. This allows us to detect libraries based on functional module completeness to address code shrinking. (2) Context-enhanced multi-level filtering: To improve robustness against obfuscation and reduce the cost of pairing, LibSleuth leverages contextual relationships to enhance feature stability and adopts a coarse-to-fine progressive matching process.We evaluated LibSleuth on datasets containing obfuscated and optimized Android apps. LibSleuth outperforms state-of-the-art academic and commercial tools in both scenarios. Under combined code shrinking and obfuscation, LibSleuth achieves an average 27.74% higher version level F1-score. Moreover, our analysis of 10,000 real world Android apps shows that 20.35% still depend on vulnerable library, demonstrating the practical utility of LibSleuth for downstream tasks.

With the dramatic increase in the number and size of software in the industry, tremendous research has been studied to automatically detect vulnerabilities. However, existing detection methods have limitations in code semantic modeling and detection granularity, which makes them unable to meet the requirements of high accuracy and fine granularity at the same time. In this paper, we propose a general framework, namely VulDL, which can effectively identify whether a given code snippet has a vulnerability and locate the specific code line where the vulnerability resides. VulDL first represents the source code as a novel semantic data structure, namely the adapted code property graph. After that, tree-based and graph-based neural networks are designed, which learn features according to the hierarchies and neighborhoods, and further realize vulnerability identification and localization. Our evaluation shows that VulDL achieves F1-scores of 98.68% and 94.85% in the identification of buffer error and resource management error vulnerabilities and 97.73% on their combined vulnerabilities. On the FFmpeg+QEMU dataset, VulDL achieves an F1-score of 59.62%, which is more effective than existing methods. Besides, VulDL can locate vulnerabilities at the statement granularity with F1-scores of 97.88%, 98.31%, and 99.16% on the evaluated datasets.

Deep neural networks are vulnerable to adversarial examples, where decision-based attacks can generate adversarial examples based solely on the predicted labels. However, these attacks typically require excessive queries to attack one example. Considering this challenge, we propose FBA (Frequency based Boundary Attack), a decision-based attack against the limitation of query efficiency. FBA incorporates a novel search process, utilizing high-frequency based importance sampling for efficient gradient estimation. Empirical results confirm the superior query efficiency of our method. Specifically, FBA surpasses SOTA attacks by achieving a 54% average improvement in query efficiency, quantified by the reduction in perturbation size within the same number of queries.

Extracting API patterns from the source code has been extensively employed to detect API misuses. However, recent studies manually provide pattern templates as prerequisites, requiring prior software knowledge and limiting their extraction scope. This paper presents APP-Miner (API path pattern miner), a novel static analysis framework for extracting API path patterns via a frequent subgraph mining technique without pattern templates. The critical insight is that API patterns usually consist of APIs’ data-related operations and are commonplace. Therefore, we define API paths as the control flow graphs composed of APIs’ data-related operations, and thereby the maximum frequent subgraphs of the API paths are the probable API path patterns. We implemented APP-Miner and extensively evaluated it on four widely used open-source software: Linux kernel, OpenSSL, FFmpeg, and Apache httpd. We found 116, 35, 3, and 3 new API misuses from the above systems, respectively. Moreover, we gained 19 CVEs.

As the first defensive layer that attacks would hit, the web application firewall (WAF) plays an indispensable role in defending against malicious web attacks like SQL injection (SQLi). With the development of cloud computing, WAF-as-a-service, as one kind of Security-as-a-service, has been proposed to facilitate the deployment, configuration, and update of WAFs in the cloud. Despite its tremendous popularity, the security vulnerabilities of WAF-as-a-service are still largely unknown, which is highly concerning given its massive usage. In this paper, we propose a general and extendable attack framework, namelyAdvSQLi, in which a minimal series of transformations are performed on the hierarchical tree representation of the original SQLi payload, such that the generated SQLi payloads can not only bypass WAF-as-a-service under black-box settings but also keep the same functionality and maliciousness as the original payload. WithAdvSQLi, we make it feasible to inspect and understand the security vulnerabilities of WAFs automatically, helping vendors make products more secure. To evaluate the attack effectiveness and efficiency ofAdvSQLi, we first employ two public datasets to generate adversarial SQLi payloads, leading to a maximum attack success rate of 100% against state-of-the-art ML-based SQLi detectors. Furthermore, to demonstrate the immediate security threats caused byAdvSQLi, we evaluate the attack effectiveness against 7 WAF-as-a-service solutions from mainstream vendors and find all of them are vulnerable toAdvSQLi. For instance,AdvSQLiachieves an attack success rate of over 79% against the F5 WAF. Through in-depth analysis of the evaluation results, we further condense out several general yet severe flaws of these vendors that cannot be easily patched.

Convolutional neural networks (CNNs) have been successfully applied to various fields. However, CNNs' overparameterization requires more memory and training time, making it unsuitable for some resource-constrained devices. To address this issue, filter pruning as one of the most efficient ways was proposed. In this article, we propose a feature-discrimination-based filter importance criterion, uniform response criterion (URC), as a key component of filter pruning. It converts the maximum activation responses into probabilities and then measures the importance of the filter through the distribution of these probabilities over classes. However, applying URC directly to global threshold pruning may cause some problems. The first problem is that some layers will be completely pruned under global pruning settings. The second problem is that global threshold pruning neglects that filters in different layers have different importance. To address these issues, we propose hierarchical threshold pruning (HTP) with URC. It performs a pruning step limited in a relatively redundant layer rather than comparing the filters' importance across all layers, which can avoid some important filters being pruned. The effectiveness of our method benefits from three techniques: 1) measuring filter importance by URC; 2) normalizing filter scores; and 3) conducting prune in relatively redundant layers. Extensive experiments on CIFAR-10/100 and ImageNet show that our method achieves the state-of-the-art performance on multiple benchmarks.

In recent years, deep learning has been widely applied in the research of automatic program repair, namely, learning-based program repair, which treats the program repair task as either a neural machine translation problem or a transformation toward the abstract syntax tree of the program. However, all existing learning-based program repair solutions have not adequately modeled the deep semantic information of the programs. To be specific, those solutions based on neural machine translation do not involve any semantic information of the programs at all, while other solutions based on abstract syntax tree transformations also do not involve information such as control flow and data flow. Additionally, the neural networks they use are also unable to sufficiently learn the semantic information. As a result, they cannot fix some bugs that involve semantic information.In this paper, we propose a new learning-based program repair approach called SGEPR. SGEPR uses a novel intermediate representation named sequence code property graph (SCPG) to model program semantic information, which can cover multiple types of semantic information in the program. SGEPR then utilizes a graph neural network based on the attention mechanism to learn the semantic information within SCPG. Finally, a well-designed prediction network is employed to generate the repair patches for the buggy program. To evaluate the performance of SGEPR, we conducted comparative experiments on a real-world dataset and the results show that SGEPR can achieve a top-3 accuracy of 56.85%, which is 15.69% higher than the state-of-the-art learning-based program repair method.

As the most popular Python software repository, PyPI has become an indispensable part of the Python ecosystem. Regrettably, the open nature of PyPI exposes end-users to substantial security risks stemming from malicious packages. Consequently, the timely and effective identification of malware within the vast number of newly-uploaded PyPI packages has emerged as a pressing concern. Existing detection methods are dependent on difficult-to-obtain explicit knowledge, such as taint sources, sinks, and malicious code patterns, rendering them susceptible to overlooking emergent malicious packages. In this paper, we present a lightweight and effective method, namely MPHunter, to detect malicious packages without requiring any explicit prior knowledge. MPHunter is founded upon two fundamental and insightful observations. First, malicious packages are considerably rarer than benign ones, and second, the functionality of installation scripts for malicious packages diverges significantly from those of benign packages, with the latter frequently forming clusters. Consequently, MPHunter utilizes clustering techniques to group the installation scripts of PyPI packages and identifies outliers. Subsequently, MPHunter ranks the outliers according to their outlierness and the distance between them and known malicious instances, thereby effectively highlighting potential evil packages. With MPHunter, we successfully identified 60 previously unknown malicious packages from a pool of 31,329 newly-uploaded packages over a two-month period. All of them have been confirmed by the PyPI official. Moreover, a manual analysis shows that MPHunter recognizes all potentially malicious installation scripts with a recall of 100% across all analyzed packages. We assert that MPHunter offers a valuable and advantageous supplement to existing detection techniques, augmenting the arsenal of software supply chain security analysis.

While the celebrated graph neural networks (GNNs) yield effective representations for individual nodes of a graph, there has been relatively less success in extending to the task of graph similarity learning. Recent work on graph similarity learning has considered either global-level graph-graph interactions or low-level node-node interactions, however, ignoring the rich cross-level interactions (e.g., between each node of one graph and the other whole graph). In this article, we propose a multilevel graph matching network (MGMN) framework for computing the graph similarity between any pair of graph-structured objects in an end-to-end fashion. In particular, the proposed MGMN consists of a node-graph matching network (NGMN) for effectively learning cross-level interactions between each node of one graph and the other whole graph, and a siamese GNN to learn global-level interactions between two input graphs. Furthermore, to compensate for the lack of standard benchmark datasets, we have created and collected a set of datasets for both the graph-graph classification and graph-graph regression tasks with different sizes in order to evaluate the effectiveness and robustness of our models. Comprehensive experiments demonstrate that MGMN consistently outperforms state-of-the-art baseline models on both the graph-graph classification and graph-graph regression tasks. Compared with previous work, multilevel graph matching network (MGMN) also exhibits stronger robustness as the sizes of the two input graphs increase.

In modern networks, administrators realize their desired functions such as network measurement in several data plane programs. They often employ the network-wide program deployment paradigm that decomposes input programs into match-action tables (MATs) while deploying each MAT on a specific programmable switch. Since MATs may be deployed on different switches, existing solutions propose the inter-switch coordination that uses the per-packet header space to deliver crucial packet processing information among switches. However, such coordination introduces non-trivial per-packet byte overhead, leading to significant end-to-end network performance degradation. In this paper, we propose Hermes, a program deployment framework that aims to minimize the per-packet byte overhead. The key idea of Hermes is to formulate the network-wide program deployment as a mixed-integer linear programming (MILP) problem with the objective of minimizing the per-packet byte overhead. In view of the NP hardness of the MILP problem, Hermes further offers a greedy-based heuristic that solves the problem in a near-optimal and timely manner. We have implemented Hermes on Tofino-based switches. Our experiments show that compared to existing frameworks, Hermes decreases the per-packet byte overhead by 156 bytes while preserving end-to-end performance in terms of flow completion time and goodput.

With the ever-increasing malware threats, malware detection plays an indispensable role in protecting information systems. Although tremendous research efforts have been made, there are still two key challenges hindering them from being applied to accurately and robustly detect malwares. Firstly, most of them represent executables with shallow features, but ignore their semantic and structural information. Secondly, they are primarily based on representations that can be easily modified by attackers and thus cannot provide robustness against adversarial attacks. To tackle the challenges, we present MalGraph, which first represents executables with hierarchical graphs and then uses an end-to-end learning framework based on graph neural networks for malware detection. In particular, a hierarchical graph consists of a function call graph that captures the interaction semantics among different functions at the inter-function level and corresponding control-flow graphs for learning the structural semantics of each function at the intra-function level. We argue the abstraction and hierarchy nature of hierarchical graphs makes them not only easy to capture rich structural information of executables, but also be immune to adversarial attacks. Evaluations show that MalGraph not only outperforms state-of-the-art malware detection, but also exhibits stronger robustness against adversarial attacks by a large margin.

As different versions of the same application might be implemented based on different platforms/programming languages, it is significantly important to build an automated migration tool for the application programming interface (API) mapping relations between different platforms/programming languages. In this paper, we propose an approach to discover API mappings based on the API documentation. We first divide the information in the API documentation into different types of entities, relations, and attributes to construct their respective API Documentation Graphs (ADGs). Then, we encode nodes, edges and triplets of ADGs and input them to a new graph neural network (GNN) for entity alignment to obtain the API mappings between the two different platforms/programming languages. Taking HarmonyOS and Android as representative cases, we evaluate our approach based on their API documentation. The results show that our approach improves top-1, top-5, and top10 accuracies by 50.57%, 56.25%, and 52.66%, respectively, compared with documentation-based baselines.

Edge intelligence has played an important role in constructing smart cities, but the vulnerability of edge nodes to adversarial attacks becomes an urgent problem. A so-called adversarial example can fool a deep learning model on an edge node for misclassification. Due to the transferability property of adversarial examples, an adversary can easily fool a black-box model by a local substitute model. Edge nodes in general have limited resources, which cannot afford a complicated defense mechanism like that on a cloud data center. To address the challenge, we propose a dynamic defense mechanism, namely EI-MTD. The mechanism first obtains robust member models of small size through differential knowledge distillation from a complicated teacher model on a cloud data center. Then, a dynamic scheduling policy, which builds on a Bayesian Stackelberg game, is applied to the choice of a target model for service. This dynamic defense mechanism can prohibit the adversary from selecting an optimal substitute model for black-box attacks. We also conduct extensive experiments to evaluate the proposed mechanism, and results show that EI-MTD could protect edge intelligence effectively against adversarial attacks in black-box settings.

Code retrieval is to find the code snippet from a large corpus of source code repositories that highly matches the query of natural language description. Recent work mainly uses natural language processing techniques to process both query texts (i.e., human natural language) and code snippets (i.e., machine programming language), however, neglecting the deep structured features of query texts and source codes, both of which contain rich semantic information. In this article, we propose an end-to-end deep graph matching and searching (DGMS) model based on graph neural networks for the task of semantic code retrieval. To this end, we first represent both natural language query texts and programming language code snippets with the unified graph-structured data, and then use the proposed graph matching and searching model to retrieve the best matching code snippet. In particular, DGMS not only captures more structural information for individual query texts or code snippets, but also learns the fine-grained similarity between them by cross-attention based semantic matching operations. We evaluate the proposed DGMS model on two public code retrieval datasets with two representative programming languages (i.e., Java and Python). Experiment results demonstrate that DGMS significantly outperforms state-of-the-art baseline models by a large margin on both datasets. Moreover, our extensive ablation studies systematically investigate and illustrate the impact of each part of DGMS.

Deep learning (DL) models are inherently vulnerable to adversarial examples - maliciously crafted inputs to trigger target DL models to misbehave - which significantly hinders the application of DL in security-sensitive domains. Intensive research on adversarial learning has led to an arms race between adversaries and defenders. Such plethora of emerging attacks and defenses raise many questions: Which attacks are more evasive, preprocessing-proof, or transferable? Which defenses are more effective, utility-preserving, or general? Are ensembles of multiple defenses more robust than individuals? Yet, due to the lack of platforms for comprehensive evaluation on adversarial attacks and defenses, these critical questions remain largely unsolved. In this paper, we present the design, implementation, and evaluation of DEEPSEC, a uniform platform that aims to bridge this gap. In its current implementation, DEEPSEC incorporates 16 state-of-the-art attacks with 10 attack utility metrics, and 13 state-of-the-art defenses with 5 defensive utility metrics. To our best knowledge, DEEPSEC is the first platform that enables researchers and practitioners to (i) measure the vulnerability of DL models, (ii) evaluate the effectiveness of various attacks/defenses, and (iii) conduct comparative studies on attacks/defenses in a comprehensive and informative manner. Leveraging DEEPSEC, we systematically evaluate the existing adversarial attack and defense methods, and draw a set of key findings, which demonstrate DEEPSEC's rich functionality, such as (1) the trade-off between misclassification and imperceptibility is empirically confirmed; (2) most defenses that claim to be universally applicable can only defend against limited types of attacks under restricted settings; (3) it is not necessary that adversarial examples with higher perturbation magnitude are easier to be detected; (4) the ensemble of multiple defenses cannot improve the overall defense capability, but can improve the lower bound of the defense effectiveness of individuals. Extensive analysis on DEEPSEC demonstrates its capabilities and advantages as a benchmark platform which can benefit future adversarial learning research.