This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants. As what we believe to be the most extensive unified cybersecurity safety benchmark to date, CyberSecEval provides a thorough evaluation of LLMs in two crucial security domains: their propensity to generate insecure code and their level of compliance when asked to assist in cyberattacks. Through a case study involving seven models from the Llama 2, Code Llama, and OpenAI GPT large language model families, CyberSecEval effectively pinpointed key cybersecurity risks. More importantly, it offered practical insights for refining these models. A significant observation from the study was the tendency of more advanced models to suggest insecure code, highlighting the critical need for integrating security considerations in the development of sophisticated LLMs. CyberSecEval, with its automated test case generation and evaluation pipeline covers a broad scope and equips LLM designers and researchers with a tool to broadly measure and enhance the cybersecurity safety properties of LLMs, contributing to the development of more secure AI systems.

Context: Static Application Security Testing Tools (SASTTs) identify software vulnerabilities to support the security and reliability of software applications. Interestingly, several studies have suggested that alternative solutions may be more effective than SASTTs due to their tendency to generate false alarms, commonly referred to as low Precision. Aim: We aim to comprehensively evaluate SASTTs, setting a reliable benchmark for assessing and finding gaps in vulnerability identification mechanisms based on SASTTs or alternatives. Method: Our SASTTs evaluation is based on a controlled, though synthetic, Java codebase. It involves an assessment of 1.5 million test executions, and it features innovative methodological features such as effort-aware accuracy metrics and method-level analysis. Results: Our findings reveal that SASTTs detect a tiny range of vulnerabilities. In contrast to prevailing wisdom, SASTTs exhibit high Precision while falling short in Recall. Conclusions: The paper suggests that enhancing Recall, alongside expanding the spectrum of detected vulnerability types, should be the primary focus for improving SASTTs or alternative approaches, such as machine learning-based vulnerability identification solutions.

Large language models (LLMs) for automatic code generation have achieved breakthroughs in several programming tasks. Their advances in competition-level programming problems have made them an essential pillar of AI-assisted pair programming, and tools such as GitHub Copilot have emerged as part of the daily programming workflow used by millions of developers. The training data for these models is usually collected from the Internet (e.g., from open-source repositories) and is likely to contain faults and security vulnerabilities. This unsanitized training data can cause the language models to learn these vulnerabilities and propagate them during the code generation procedure. While these models have been extensively assessed for their ability to produce functionally correct programs, there remains a lack of comprehensive investigations and benchmarks addressing the security aspects of these models. In this work, we propose a method to systematically study the security issues of code language models to assess their susceptibility to generating vulnerable code. To this end, we introduce the first approach to automatically find generated code that contains vulnerabilities in black-box code generation models. To achieve this, we present an approach to approximate inversion of the black-box code generation models based on few-shot prompting. We evaluate the effectiveness of our approach by examining code language models in generating high-risk security weaknesses. Furthermore, we establish a collection of diverse non-secure prompts for various vulnerability scenarios using our method. This dataset forms a benchmark for evaluating and comparing the security weaknesses in code language models.

The increasing trend of using Large Language Models (LLMs) for code generation raises the question of their capability to generate trustworthy code. While many researchers are exploring the utility of code generation for uncovering software vulnerabilities, one crucial but often overlooked aspect is the security Application Programming Interfaces (APIs). APIs play an integral role in upholding software security, yet effectively integrating security APIs presents substantial challenges. This leads to inadvertent misuse by developers, thereby exposing software to vulnerabilities. To overcome these challenges, developers may seek assistance from LLMs. In this paper, we systematically assess ChatGPT's trustworthiness in code generation for security API use cases in Java. To conduct a thorough evaluation, we compile an extensive collection of 48 programming tasks for 5 widely used security APIs. We employ both automated and manual approaches to effectively detect security API misuse in the code generated by ChatGPT for these tasks. Our findings are concerning: around 70% of the code instances across 30 attempts per task contain security API misuse, with 20 distinct misuse types identified. Moreover, for roughly half of the tasks, this rate reaches 100%, indicating that there is a long way to go before developers can rely on ChatGPT to securely implement security API code.