Large language models (LLMs) have been widely adopted across diverse software engineering domains, such as code generation, program repair, and vulnerability detection. These applications require understanding beyond surface-level code patterns: value propagation, control flow, and interdependence between program elements. However, existing benchmarks primarily evaluate end-to-end outcomes, such as whether code is correctly repaired or generated, leaving the models ability for program semantic reasoning underexplored. This work presents CoRe, a high-quality, human-verified benchmark designed to evaluate LLMs on fundamental static analysis tasks. CoRe includes 12,553 task instances spanning data dependency, control dependency, and information flow across programs written in C/C++, Java, and Python. To ensure semantic diversity and reasoning complexity, we propose a semantics-aware diverse sampling strategy that selects targets and task instances based on structural coverage and dependency depth. We evaluate 10 mainstream LLMs and show that, while they perform well at identifying dependencies, models still struggle with tasks that require deeper semantic understanding and multi-step reasoning. We further conduct qualitative analyses to uncover key challenges, such as complex control structures and backward dependency patterns, offering insights into improving LLMs code reasoning capabilities.
Recent advancements in large language models (LLMs) have shown promise for automated vulnerability detection and repair in software systems. This paper investigates the performance of GPT-4o in repairing Java vulnerabilities from a widely used dataset (Vul4J), exploring how different contextual information affects automated vulnerability repair (AVR) capabilities. We compare the latest GPT-4o's performance against previous results with GPT-4 using identical prompts. We evaluated nine additional prompts crafted by us that contain various contextual information such as CWE or CVE information, and manually extracted code contexts. Each prompt was executed three times on 42 vulnerabilities, and the resulting fix candidates were validated using Vul4J's automated testing framework. Our results show that GPT-4o performed 11.9\% worse on average than GPT-4 with the same prompt, but was able to fix 10.5\% more distinct vulnerabilities in the three runs together. CVE information significantly improved repair rates, while the length of the task description had minimal impact. Combining CVE guidance with manually extracted code context resulted in the best performance. Using our \textsc{Top}-3 prompts together, GPT-4o repaired 26 (62\%) vulnerabilities at least once, outperforming both the original baseline (40\%) and its reproduction (45\%), suggesting that ensemble prompt strategies could improve vulnerability repair in zero-shot settings.
Smart contract vulnerability detection remains a major challenge in blockchain security. Existing vulnerability detection methods face two main issues: (1) Existing datasets lack comprehensive coverage and high-quality explanations for preference learning. (2) Large language models (LLMs) often struggle with accurately interpreting specific concepts in smart contract security. Empirical analysis shows that even after continual pre-training (CPT) and supervised fine-tuning (SFT), LLMs may misinterpret the execution order of state changes, resulting in incorrect explanations despite making correct detection decisions. To address these challenges, we propose Smart-LLaMA-DPO based on LLaMA-3.1-8B. We construct a comprehensive dataset covering four major vulnerability types and machine-unauditable vulnerabilities, including precise labels, explanations, and locations for SFT, as well as high-quality and low-quality output pairs for Direct Preference Optimization (DPO). Second, we perform CPT using large-scale smart contract to enhance the LLM's understanding of specific security practices in smart contracts. Futhermore, we conduct SFT with our comprehensive dataset. Finally, we apply DPO, leveraging human feedback and a specially designed loss function that increases the probability of preferred explanations while reducing the likelihood of non-preferred outputs. We evaluate Smart-LLaMA-DPO on four major vulnerability types: reentrancy, timestamp dependence, integer overflow/underflow, and delegatecall, as well as machine-unauditable vulnerabilities. Our method significantly outperforms state-of-the-art baselines, with average improvements of 10.43% in F1 score and 7.87% in accuracy. Moreover, both LLM evaluation and human evaluation confirm that our method generates more correct, thorough, and clear explanations.
Ensuring the security of complex system-on-chips (SoCs) designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and adaptability. The advent of large language models (LLMs), with their remarkable capabilities in natural language understanding, code generation, and advanced reasoning, presents a new paradigm for tackling these issues. Moving beyond monolithic models, an agentic approach allows for the creation of multi-agent systems where specialized LLMs collaborate to solve complex problems more effectively. Recognizing this opportunity, we introduce SV-LLM, a novel multi-agent assistant system designed to automate and enhance SoC security verification. By integrating specialized agents for tasks like verification question answering, security asset identification, threat modeling, test plan and property generation, vulnerability detection, and simulation-based bug validation, SV-LLM streamlines the workflow. To optimize their performance in these diverse tasks, agents leverage different learning paradigms, such as in-context learning, fine-tuning, and retrieval-augmented generation (RAG). The system aims to reduce manual intervention, improve accuracy, and accelerate security analysis, supporting proactive identification and mitigation of risks early in the design cycle. We demonstrate its potential to transform hardware security practices through illustrative case studies and experiments that showcase its applicability and efficacy.
Vulnerability datasets used for ML testing implicitly contain retrospective information. When tested on the field, one can only use the labels available at the time of training and testing (e.g. seen and assumed negatives). As vulnerabilities are discovered across calendar time, labels change and past performance is not necessarily aligned with future performance. Past works only considered the slices of the whole history (e.g. DiverseVUl) or individual differences between releases (e.g. Jimenez et al. ESEC/FSE 2019). Such approaches are either too optimistic in training (e.g. the whole history) or too conservative (e.g. consecutive releases). We propose a method to restructure a dataset into a series of datasets in which both training and testing labels change to account for the knowledge available at the time. If the model is actually learning, it should improve its performance over time as more data becomes available and data becomes more stable, an effect that can be checked with the Mann-Kendall test. We validate our methodology for vulnerability detection with 4 time-based datasets (3 projects from BigVul dataset + Vuldeepecker's NVD) and 5 ML models (Code2Vec, CodeBERT, LineVul, ReGVD, and Vuldeepecker). In contrast to the intuitive expectation (more retrospective information, better performance), the trend results show that performance changes inconsistently across the years, showing that most models are not learning.
Large language models (LLMs) demonstrate considerable proficiency in numerous coding-related tasks; however, their capabilities in detecting software vulnerabilities remain limited. This limitation primarily stems from two factors: (1) the absence of reasoning data related to vulnerabilities, which hinders the models' ability to capture underlying vulnerability patterns; and (2) their focus on learning semantic representations rather than the reason behind them, thus failing to recognize semantically similar vulnerability samples. Furthermore, the development of LLMs specialized in vulnerability detection is challenging, particularly in environments characterized by the scarcity of high-quality datasets. In this paper, we propose a novel framework ReVD that excels at mining vulnerability patterns through reasoning data synthesizing and vulnerability-specific preference optimization. Specifically, we construct forward and backward reasoning processes for vulnerability and corresponding fixed code, ensuring the synthesis of high-quality reasoning data. Moreover, we design the triplet supervised fine-tuning followed by curriculum online preference optimization for enabling ReVD to better understand vulnerability patterns. The extensive experiments conducted on PrimeVul and SVEN datasets demonstrate that ReVD sets new state-of-the-art for LLM-based software vulnerability detection, e.g., 12.24\%-22.77\% improvement in the accuracy. The source code and data are available at https://github.com/Xin-Cheng-Wen/PO4Vul.
Smart contracts, integral to blockchain ecosystems, enable decentralized applications to execute predefined operations without intermediaries. Their ability to enforce trustless interactions has made them a core component of platforms such as Ethereum. Vulnerabilities such as numerical overflows, reentrancy attacks, and improper access permissions have led to the loss of millions of dollars throughout the blockchain and smart contract sector. Traditional smart contract auditing techniques such as manual code reviews and formal verification face limitations in scalability, automation, and adaptability to evolving development patterns. As a result, AI-based solutions have emerged as a promising alternative, offering the ability to learn complex patterns, detect subtle flaws, and provide scalable security assurances. This paper examines novel AI-driven techniques for vulnerability detection in smart contracts, focusing on machine learning, deep learning, graph neural networks, and transformer-based models. This paper analyzes how each technique represents code, processes semantic information, and responds to real world vulnerability classes. We also compare their strengths and weaknesses in terms of accuracy, interpretability, computational overhead, and real time applicability. Lastly, it highlights open challenges and future opportunities for advancing this domain.
The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code. In this work, we introduce SafeGenBench, a benchmark specifically designed to assess the security of LLM-generated code. The dataset encompasses a wide range of common software development scenarios and vulnerability types. Building upon this benchmark, we develop an automatic evaluation framework that leverages both static application security testing(SAST) and LLM-based judging to assess the presence of security vulnerabilities in model-generated code. Through the empirical evaluation of state-of-the-art LLMs on SafeGenBench, we reveal notable deficiencies in their ability to produce vulnerability-free code. Our findings highlight pressing challenges and offer actionable insights for future advancements in the secure code generation performance of LLMs. The data and code will be released soon.
Binary code similarity detection (BCSD) serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming at misleading the models to generate erroneous predictions. Prior works have explored various approaches to generating semantic-preserving variants, i.e., adversarial samples, to evaluate the robustness of the models against adversarial attacks. However, they have mainly relied on heuristic criteria or iterative greedy algorithms to locate salient code influencing the model output, failing to operate on a solid theoretical basis. Moreover, when processing programs with high complexities, such attacks tend to be time-consuming. In this work, we propose a novel optimization for adversarial attacks against BCSD models. In particular, we aim to improve the attacks in a challenging scenario, where the attack goal is to limit the model predictions to a specific range, i.e., the targeted attacks. Our attack leverages the superior capability of black-box, model-agnostic explainers in interpreting the model decision boundaries, thereby pinpointing the critical code snippet to apply semantic-preserving perturbations. The evaluation results demonstrate that compared with the state-of-the-art attacks, the proposed attacks achieve higher attack success rate in almost all scenarios, while also improving the efficiency and transferability. Our real-world case studies on vulnerability detection and classification further demonstrate the security implications of our attacks, highlighting the urgent need to further enhance the robustness of existing BCSD models.
Software vulnerabilities pose significant security threats, requiring effective mitigation. While Automated Program Repair (APR) has advanced in fixing general bugs, vulnerability patching, a security-critical aspect of APR remains underexplored. This study investigates pre-trained language models, CodeBERT and CodeT5, for automated vulnerability patching across six datasets and four languages. We evaluate their accuracy and generalization to unknown vulnerabilities. Results show that while both models face challenges with fragmented or sparse context, CodeBERT performs comparatively better in such scenarios, whereas CodeT5 excels in capturing complex vulnerability patterns. CodeT5 also demonstrates superior scalability. Furthermore, we test fine-tuned models on both in-distribution (trained) and out-of-distribution (unseen) datasets. While fine-tuning improves in-distribution performance, models struggle to generalize to unseen data, highlighting challenges in robust vulnerability detection. This study benchmarks model performance, identifies limitations in generalization, and provides actionable insights to advance automated vulnerability patching for real-world security applications.
Large Language Models (LLMs) are being extensively used for cybersecurity purposes. One of them is the detection of vulnerable codes. For the sake of efficiency and effectiveness, compression and fine-tuning techniques are being developed, respectively. However, they involve spending substantial computational efforts. In this vein, we analyse how Linear Probes (LPs) can be used to provide an estimation on the performance of a compressed LLM at an early phase -- before fine-tuning. We also show their suitability to set the cut-off point when applying layer pruning compression. Our approach, dubbed $LPASS$, is applied in BERT and Gemma for the detection of 12 of MITRE's Top 25 most dangerous vulnerabilities on 480k C/C++ samples. LPs can be computed in 142.97 s. and provide key findings: (1) 33.3 \% and 72.2\% of layers can be removed, respectively, with no precision loss; (2) they provide an early estimate of the post-fine-tuning and post-compression model effectiveness, with 3\% and 8.68\% as the lowest and average precision errors, respectively. $LPASS$-based LLMs outperform the state of the art, reaching 86.9\% of accuracy in multi-class vulnerability detection. Interestingly, $LPASS$-based compressed versions of Gemma outperform the original ones by 1.6\% of F1-score at a maximum while saving 29.4 \% and 23.8\% of training and inference time and 42.98\% of model size.
The current landscape of system-on-chips (SoCs) security verification faces challenges due to manual, labor-intensive, and inflexible methodologies. These issues limit the scalability and effectiveness of security protocols, making bug detection at the Register-Transfer Level (RTL) difficult. This paper proposes a new framework named BugWhisperer that utilizes a specialized, fine-tuned Large Language Model (LLM) to address these challenges. By enhancing the LLM's hardware security knowledge and leveraging its capabilities for text inference and knowledge transfer, this approach automates and improves the adaptability and reusability of the verification process. We introduce an open-source, fine-tuned LLM specifically designed for detecting security vulnerabilities in SoC designs. Our findings demonstrate that this tailored LLM effectively enhances the efficiency and flexibility of the security verification process. Additionally, we introduce a comprehensive hardware vulnerability database that supports this work and will further assist the research community in enhancing the security verification process.
As Large Language Models (LLMs) evolve in understanding and generating code, accurately evaluating their reliability in analyzing source code vulnerabilities becomes increasingly vital. While studies have examined LLM capabilities in tasks like vulnerability detection and repair, they often overlook the importance of both structure and semantic reasoning crucial for trustworthy vulnerability analysis. To address this gap, we introduce SV-TrustEval-C, a benchmark designed to evaluate LLMs' abilities for vulnerability analysis of code written in the C programming language through two key dimensions: structure reasoning - assessing how models identify relationships between code elements under varying data and control flow complexities; and semantic reasoning - examining their logical consistency in scenarios where code is structurally and semantically perturbed. Our results show that current LLMs are far from satisfactory in understanding complex code relationships and that their vulnerability analyses rely more on pattern matching than on robust logical reasoning. These findings underscore the effectiveness of the SV-TrustEval-C benchmark and highlight critical areas for enhancing the reasoning capabilities and trustworthiness of LLMs in real-world vulnerability analysis tasks. Our initial benchmark dataset is publicly available.
Large Language Models (LLMs) are being used more and more for various coding tasks, including to help coders identify bugs and are a promising avenue to support coders in various tasks including vulnerability detection -- particularly given the flexibility of such generative AI models and tools. Yet for many tasks it may not be suitable to use LLMs, for which it may be more suitable to use smaller language models that can fit and easily execute and train on a developer's computer. In this paper we explore and evaluate whether smaller language models can be fine-tuned to achieve reasonable results for a niche area: vulnerability detection -- specifically focusing on detecting the reentrancy bug in Solidity smart contracts.
Large Language Model (LLM) agents can automate cybersecurity tasks and can adapt to the evolving cybersecurity landscape without re-engineering. While LLM agents have demonstrated cybersecurity capabilities on Capture-The-Flag (CTF) competitions, they have two key limitations: accessing latest cybersecurity expertise beyond training data, and integrating new knowledge into complex task planning. Knowledge-based approaches that incorporate technical understanding into the task-solving automation can tackle these limitations. We present CRAKEN, a knowledge-based LLM agent framework that improves cybersecurity capability through three core mechanisms: contextual decomposition of task-critical information, iterative self-reflected knowledge retrieval, and knowledge-hint injection that transforms insights into adaptive attack strategies. Comprehensive evaluations with different configurations show CRAKEN's effectiveness in multi-stage vulnerability detection and exploitation compared to previous approaches. Our extensible architecture establishes new methodologies for embedding new security knowledge into LLM-driven cybersecurity agentic systems. With a knowledge database of CTF writeups, CRAKEN obtained an accuracy of 22% on NYU CTF Bench, outperforming prior works by 3% and achieving state-of-the-art results. On evaluation of MITRE ATT&CK techniques, CRAKEN solves 25-30% more techniques than prior work, demonstrating improved cybersecurity capabilities via knowledge-based execution. We make our framework open source to public https://github.com/NYU-LLM-CTF/nyuctf_agents_craken.
Large Language Models (LLMs) have shown great promise in code analysis and auditing; however, they still struggle with hallucinations and limited context-aware reasoning. We introduce SmartAuditFlow, a novel Plan-Execute framework that enhances smart contract security analysis through dynamic audit planning and structured execution. Unlike conventional LLM-based auditing approaches that follow fixed workflows and predefined steps, SmartAuditFlow dynamically generates and refines audit plans based on the unique characteristics of each smart contract. It continuously adjusts its auditing strategy in response to intermediate LLM outputs and newly detected vulnerabilities, ensuring a more adaptive and precise security assessment. The framework then executes these plans step by step, applying a structured reasoning process to enhance vulnerability detection accuracy while minimizing hallucinations and false positives. To further improve audit precision, SmartAuditFlow integrates iterative prompt optimization and external knowledge sources, such as static analysis tools and Retrieval-Augmented Generation (RAG). This ensures audit decisions are contextually informed and backed by real-world security knowledge, producing comprehensive security reports. Extensive evaluations across multiple benchmarks demonstrate that SmartAuditFlow outperforms existing methods, achieving 100 percent accuracy on common and critical vulnerabilities, 41.2 percent accuracy for comprehensive coverage of known smart contract weaknesses in real-world projects, and successfully identifying all 13 tested CVEs. These results highlight SmartAuditFlow's scalability, cost-effectiveness, and superior adaptability over traditional static analysis tools and contemporary LLM-based approaches, establishing it as a robust solution for automated smart contract auditing.
Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large Language Models(LLMs) in code-related tasks, such as testing, researchers have explored their potential for vulnerabilities analysis. This study evaluates the potential of large language models (LLMs), such as GPT-4, as an alternative approach for automated testing for vulnerability detection. In particular, LLMs have demonstrated advanced contextual understanding and adaptability, making them promising candidates for identifying nuanced security vulnerabilities within code. To evaluate this potential, we applied LLM-based analysis to six high-profile GitHub projects-Django, Flask, TensorFlow, Scikit-learn, PyTorch, and Langchain-each with over 50,000 stars and extensive adoption across software development and academic research. Our analysis assesses both the strengths and limitations of LLMs in detecting command injection vulnerabilities, evaluating factors such as detection accuracy, efficiency, and practical integration into development workflows. In addition, we provide a comparative analysis of different LLM tools to identify those most suitable for security applications. Our findings offer guidance for developers and security researchers on leveraging LLMs as innovative and automated approaches to enhance software security.
Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we introduce VulTrial, a courtroom-inspired multi-agent framework designed to enhance automated vulnerability detection. It employs four role-specific agents, which are security researcher, code author, moderator, and review board. Through extensive experiments using GPT-3.5 and GPT-4o we demonstrate that Vultrial outperforms single-agent and multi-agent baselines. Using GPT-4o, VulTrial improves the performance by 102.39% and 84.17% over its respective baseline. Additionally, we show that role-specific instruction tuning in multi-agent with small data (50 pair samples) improves the performance of VulTrial further by 139.89% and 118.30%. Furthermore, we analyze the impact of increasing the number of agent interactions on VulTrial's overall performance. While multi-agent setups inherently incur higher costs due to increased token usage, our findings reveal that applying VulTrial to a cost-effective model like GPT-3.5 can improve its performance by 69.89% compared to GPT-4o in a single-agent setting, at a lower overall cost.
Code security and usability are both essential for various coding assistant applications driven by large language models (LLMs). Current code security benchmarks focus solely on single evaluation task and paradigm, such as code completion and generation, lacking comprehensive assessment across dimensions like secure code generation, vulnerability repair and discrimination. In this paper, we first propose CoV-Eval, a multi-task benchmark covering various tasks such as code completion, vulnerability repair, vulnerability detection and classification, for comprehensive evaluation of LLM code security. Besides, we developed VC-Judge, an improved judgment model that aligns closely with human experts and can review LLM-generated programs for vulnerabilities in a more efficient and reliable way. We conduct a comprehensive evaluation of 20 proprietary and open-source LLMs. Overall, while most LLMs identify vulnerable codes well, they still tend to generate insecure codes and struggle with recognizing specific vulnerability types and performing repairs. Extensive experiments and qualitative analyses reveal key challenges and optimization directions, offering insights for future research in LLM code security.
Software vulnerabilities such as buffer overflows and SQL injections are a major source of security breaches. Traditional methods for vulnerability detection remain essential but are limited by high false positive rates, scalability issues, and reliance on manual effort. These constraints have driven interest in AI-based approaches to automated vulnerability detection and secure code generation. While Large Language Models (LLMs) have opened new avenues for classification tasks, their complexity and opacity pose challenges for interpretability and deployment. Sparse Autoencoder offer a promising solution to this problem. We explore whether SAEs can serve as a lightweight, interpretable alternative for bug detection in Java functions. We evaluate the effectiveness of SAEs when applied to representations from GPT-2 Small and Gemma 2B, examining their capacity to highlight buggy behaviour without fine-tuning the underlying LLMs. We found that SAE-derived features enable bug detection with an F1 score of up to 89%, consistently outperforming fine-tuned transformer encoder baselines. Our work provides the first empirical evidence that SAEs can be used to detect software bugs directly from the internal representations of pretrained LLMs, without any fine-tuning or task-specific supervision.