Evaluating ChatGPT for Software Vulnerability Tasks: A Comparative Analysis

With its impressive 1.7 trillion parameters, ChatGPT has emerged as a powerful language model. However, its applicability to code-oriented tasks, such as software vulnerability analysis and repair, remains relatively unexplored. In this article, we delve into the evaluation of ChatGPT against code-specific models, specifically examining its performance on four vulnerability tasks using the Big-Vul and CVEFixes datasets. This comprehensive analysis sheds light on the potential limitations of using ChatGPT for software vulnerability tasks while emphasizing the need for domain-specific fine-tuning.

Evaluation of ChatGPT against code-specific models

To comprehensively evaluate ChatGPT’s performance, security analysts conducted experiments using the Big-Vul and CVEFixes datasets. These datasets provide a comprehensive set of vulnerability tasks, enabling a thorough comparison of ChatGPT against baseline methods. The evaluation focused on the F1-measure and top-10 accuracy metrics.

The results of the evaluation revealed that ChatGPT achieved an F1-measure of 10% and 29% on the Big-Vul and CVEFixes datasets, respectively. These scores were significantly lower compared to the other baseline methods. Similarly, the top-10 accuracy of ChatGPT was 25% and 65%, which again reflected the lowest performance among the examined models.

Analysis of Multiclass Accuracy

In addition to F1-measure and top-10 accuracy, multiclass accuracy was also considered as a crucial performance indicator. The analysis revealed that ChatGPT achieved the lowest multiclass accuracy of 13%, showcasing a striking 45%-52% difference from the best baseline model. These outcomes underscore the challenges faced by ChatGPT in accurately classifying vulnerability tasks across multiple classes.

Evaluation of Severity Estimation

Severity estimation holds paramount importance in vulnerability analysis to prioritize remediation efforts. However, ChatGPT’s performance in this regard proved to be unsatisfactory. The evaluation indicated that ChatGPT exhibited the highest mean squared error (MSE) of 5.4 and 5.85, implying its inaccurate severity estimation compared to the other baselines. This finding raises concerns about relying on ChatGPT for precise severity estimation in vulnerability assessment.

Assessment of Repair Patch Generation

One vital aspect of vulnerability repair is the generation of correct repair patches. Regrettably, ChatGPT failed to generate accurate repair patches in this evaluation. On the other hand, the baseline models demonstrated success in rectifying vulnerable functions, correctly repairing 7% to 30% of them. This stark contrast highlights the limitations of ChatGPT in generating effective repair solutions.

Limitations of fine-tuning

Fine-tuning is a commonly employed technique to optimize language models for specific tasks. However, in the case of ChatGPT, fine-tuning for vulnerability tasks is not viable due to proprietary parameters. This constraint further underlines the challenges in adapting ChatGPT directly for software vulnerability tasks.

The Importance of Domain-specific Fine-tuning

The analysis of ChatGPT’s performance in vulnerability tasks underscores the significance of domain-specific fine-tuning. The complexity and specificity of software vulnerability tasks necessitate the customization of language models like ChatGPT to better suit the requirements. This suggests the need for further research and work on fine-tuning or adapting ChatGPT specifically for software vulnerability tasks.

Comparison with previous studies

While previous studies have examined the effectiveness of large language models in automated program repair, they have not accounted for the latest versions of ChatGPT. This article bridges that gap by shedding light on the specific performance of ChatGPT in software vulnerability tasks. Additionally, the notable disparities in results indicate the necessity for dedicated exploration of ChatGPT’s potential in this domain.

In conclusion, the evaluation of ChatGPT for software vulnerability tasks reveals its limitations in comparison to code-specific models. The lower F1-measure, top-10 accuracy, multiclass accuracy, inaccurate severity estimation, and inability to generate correct repair patches highlight the challenges faced by ChatGPT in this context. The proprietary nature of its parameters further restricts fine-tuning for vulnerability tasks. As such, this study emphasizes the need for additional research and efforts to fine-tune or tailor ChatGPT specifically for software vulnerability analysis and repair. By addressing these challenges, ChatGPT could potentially be leveraged more effectively in securing software systems in the future.

Explore more

How Is AI Revolutionizing Email Marketing Strategies?

Setting the Stage for Digital Communication Evolution In today’s hyper-connected digital landscape, businesses send billions of emails daily, yet only a fraction capture attention amid overflowing inboxes, pushing marketers to seek innovative solutions. Artificial Intelligence (AI) has emerged as a game-changer in transforming email marketing from a generic broadcast tool into a precision-driven strategy. With the ability to analyze vast

How Is Embedded Finance Transforming UK Brand Experiences?

Imagine a world where purchasing a new gadget at a retail store instantly offers tailored financing options right at checkout, or where booking a vacation seamlessly includes travel insurance within the same app. This is the reality shaped by embedded finance, a transformative technology integrating financial services into non-financial platforms. As digital ecosystems continue to dominate consumer interactions in 2025,

Paid Content Marketing Triumphs in the AI Era over Earned Media

In the rapidly changing arena of digital marketing, a profound transformation is reshaping how brands connect with audiences, marking a significant shift in strategy. Once a dominant force, earned media—those organic news features or viral social media moments—has been dethroned as the go-to strategy for growth among businesses, musicians, and creators. Now, paid content marketing has surged to the forefront,

Job Openings Drop in July, Yet Hiring Remains Strong

Overview of the U.S. Labor Market In the heat of summer, as businesses and workers navigate an ever-shifting economic landscape, a striking statistic emerges from the U.S. labor market: job openings have dipped to 7.2 million in July, down from 7.4 million just a month prior, raising eyebrows especially when juxtaposed with the robust hiring figures of 5.3 million for

Trend Analysis: Cooling US Labor Market Dynamics

Introduction In a startling reflection of economic headwinds, US private sector job growth plummeted to a mere 54,000 in August, nearly half of the previous month’s tally of 106,000, signaling a profound slowdown in labor market momentum. This sharp decline arrives at a critical juncture, with economic uncertainty casting a long shadow, policy debates intensifying, and political figures like President