The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains vulnerabilities and lacks essential defensive programming constructs. This work focuses on examining and evaluating the security of LLM-generated code, particularly in the context of C/C++. We categorized known vulnerabilities using the Common Weakness Enumeration (CWE) and, to study their criticality, mapped them to CVEs. We used ten different LLMs for code generation and analyzed the outputs through static analysis. The amount of CWEs present in AI-generated code is concerning. Our findings highlight the need for developers to be cautious when using LLM-generated code. This study provides valuable insights to advance automated code generation and encourage further research in this domain.

Cyber threat intelligence (CTI) is central to modern cybersecurity, providing critical insights for detecting and mitigating evolving threats. With the natural language understanding and reasoning capabilities of large language models (LLMs), there is increasing interest in applying them to CTI, which calls for benchmarks that can rigorously evaluate their performance. Several early efforts have studied LLMs on some CTI tasks but remain limited: (i) they adopt only closed-book settings, relying on parametric knowledge without leveraging CTI knowledge bases; (ii) they cover only a narrow set of tasks, lacking a systematic view of the CTI landscape; and (iii) they restrict evaluation to single-source analysis, unlike realistic scenarios that require reasoning across multiple sources. To fill these gaps, we present CTIArena, the first benchmark for evaluating LLM performance on heterogeneous, multi-source CTI under knowledge-augmented settings. CTIArena spans three categories, structured, unstructured, and hybrid, further divided into nine tasks that capture the breadth of CTI analysis in modern security operations. We evaluate ten widely used LLMs and find that most struggle in closed-book setups but show noticeable gains when augmented with security-specific knowledge through our designed retrieval-augmented techniques. These findings highlight the limitations of general-purpose LLMs and the need for domain-tailored techniques to fully unlock their potential for CTI.

Despite their remarkable success, large language models (LLMs) have shown limited ability on applied tasks such as vulnerability detection. We investigate various prompting strategies for vulnerability detection and, as part of this exploration, propose a prompting strategy that integrates natural language descriptions of vulnerabilities with a contrastive chain-of-thought reasoning approach, augmented using contrastive samples from a synthetic dataset. Our study highlights the potential of LLMs to detect vulnerabilities by integrating natural language descriptions, contrastive reasoning, and synthetic examples into a comprehensive prompting framework. Our results show that this approach can enhance LLM understanding of vulnerabilities. On a high-quality vulnerability detection dataset such as SVEN, our prompting strategies can improve accuracies, F1-scores, and pairwise accuracies by 23%, 11%, and 14%, respectively.

This paper explores the potential of contextualized word embeddings (CWEs) as a new tool in the history, philosophy, and sociology of science (HPSS) for studying contextual and evolving meanings of scientific concepts. Using the term "Planck" as a test case, I evaluate five BERT-based models with varying degrees of domain-specific pretraining, including my custom model Astro-HEP-BERT, trained on the Astro-HEP Corpus, a dataset containing 21.84 million paragraphs from 600,000 articles in astrophysics and high-energy physics. For this analysis, I compiled two labeled datasets: (1) the Astro-HEP-Planck Corpus, consisting of 2,900 labeled occurrences of "Planck" sampled from 1,500 paragraphs in the Astro-HEP Corpus, and (2) a physics-related Wikipedia dataset comprising 1,186 labeled occurrences of "Planck" across 885 paragraphs. Results demonstrate that the domain-adapted models outperform the general-purpose ones in disambiguating the target term, predicting its known meanings, and generating high-quality sense clusters, as measured by a novel purity indicator I developed. Additionally, this approach reveals semantic shifts in the target term over three decades in the unlabeled Astro-HEP Corpus, highlighting the emergence of the Planck space mission as a dominant sense. The study underscores the importance of domain-specific pretraining for analyzing scientific language and demonstrates the cost-effectiveness of adapting pretrained models for HPSS research. By offering a scalable and transferable method for modeling the meanings of scientific concepts, CWEs open up new avenues for investigating the socio-historical dynamics of scientific discourses.

The capability of generating high-quality source code using large language models (LLMs) reduces software development time and costs. However, they often introduce security vulnerabilities due to training on insecure open-source data. This highlights the need for ensuring secure and functional code generation. This paper introduces PromSec, an algorithm for prom optimization for secure and functioning code generation using LLMs. In PromSec, we combine 1) code vulnerability clearing using a generative adversarial graph neural network, dubbed as gGAN, to fix and reduce security vulnerabilities in generated codes and 2) code generation using an LLM into an interactive loop, such that the outcome of the gGAN drives the LLM with enhanced prompts to generate secure codes while preserving their functionality. Introducing a new contrastive learning approach in gGAN, we formulate code-clearing and generation as a dual-objective optimization problem, enabling PromSec to notably reduce the number of LLM inferences. PromSec offers a cost-effective and practical solution for generating secure, functional code. Extensive experiments conducted on Python and Java code datasets confirm that PromSec effectively enhances code security while upholding its intended functionality. Our experiments show that while a state-of-the-art approach fails to address all code vulnerabilities, PromSec effectively resolves them. Moreover, PromSec achieves more than an order-of-magnitude reduction in operation time, number of LLM queries, and security analysis costs. Furthermore, prompts optimized with PromSec for a certain LLM are transferable to other LLMs across programming languages and generalizable to unseen vulnerabilities in training. This study is a step in enhancing the trustworthiness of LLMs for secure and functional code generation, supporting their integration into real-world software development.

Pretrained language model (PLM) hidden states are frequently employed as contextual word embeddings (CWE): high-dimensional representations that encode semantic information given linguistic context. Across many areas of computational linguistics research, similarity between CWEs is interpreted as semantic similarity. However, it remains unclear exactly what information is encoded in PLM hidden states. We investigate this practice by probing PLM representations using minimal orthographic noise. We expect that if CWEs primarily encode semantic information, a single character swap in the input word will not drastically affect the resulting representation,given sufficient linguistic context. Surprisingly, we find that CWEs generated by popular PLMs are highly sensitive to noise in input data, and that this sensitivity is related to subword tokenization: the fewer tokens used to represent a word at input, the more sensitive its corresponding CWE. This suggests that CWEs capture information unrelated to word-level meaning and can be manipulated through trivial modifications of input data. We conclude that these PLM-derived CWEs may not be reliable semantic proxies, and that caution is warranted when interpreting representational similarity

Modern hardware designs have grown increasingly efficient and complex. However, they are often susceptible to Common Weakness Enumerations (CWEs). This paper is focused on the formal verification of CWEs in a dataset of hardware designs written in SystemVerilog from Regenerative Artificial Intelligence (AI) powered by Large Language Models (LLMs). We applied formal verification to categorize each hardware design as vulnerable or CWE-free. This dataset was generated by 4 different LLMs and features a unique set of designs for each of the 10 CWEs we target in our paper. We have associated the identified vulnerabilities with CWE numbers for a dataset of 60,000 generated SystemVerilog Register Transfer Level (RTL) code. It was also found that most LLMs are not aware of any hardware CWEs; hence they are usually not considered when generating the hardware code. Our study reveals that approximately 60% of the hardware designs generated by LLMs are prone to CWEs, posing potential safety and security risks. The dataset could be ideal for training LLMs and Machine Learning (ML) algorithms to abstain from generating CWE-prone hardware designs. With the increasing complexity of project requirements, hardware designs have also evolved in a similar way. Modern System-on-Chip (SoC) designs are very complex and often require smart methodologies to address simple problems.

Sonatype's 2023 report found that 97% of developers and security leads integrate generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), into their development process. Concerns about the security implications of this trend have been raised. Developers are now weighing the benefits and risks of LLMs against other relied-upon information sources, such as StackOverflow (SO), requiring empirical data to inform their choice. In this work, our goal is to raise software developers awareness of the security implications when selecting code snippets by empirically comparing the vulnerabilities of ChatGPT and StackOverflow. To achieve this, we used an existing Java dataset from SO with security-related questions and answers. Then, we asked ChatGPT the same SO questions, gathering the generated code for comparison. After curating the dataset, we analyzed the number and types of Common Weakness Enumeration (CWE) vulnerabilities of 108 snippets from each platform using CodeQL. ChatGPT-generated code contained 248 vulnerabilities compared to the 302 vulnerabilities found in SO snippets, producing 20% fewer vulnerabilities with a statistically significant difference. Additionally, ChatGPT generated 19 types of CWE, fewer than the 22 found in SO. Our findings suggest developers are under-educated on insecure code propagation from both platforms, as we found 274 unique vulnerabilities and 25 types of CWE. Any code copied and pasted, created by AI or humans, cannot be trusted blindly, requiring good software engineering practices to reduce risk. Future work can help minimize insecure code propagation from any platform.

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.

Large language models (large LMs) are increasingly trained on massive codebases and used to generate code. However, LMs lack awareness of security and are found to frequently produce unsafe code. This work studies the security of LMs along two important axes: (i) security hardening, which aims to enhance LMs' reliability in generating secure code, and (ii) adversarial testing, which seeks to evaluate LMs' security at an adversarial standpoint. We address both of these by formulating a new security task called controlled code generation. The task is parametric and takes as input a binary property to guide the LM to generate secure or unsafe code, while preserving the LM's capability of generating functionally correct code. We propose a novel learning-based approach called SVEN to solve this task. SVEN leverages property-specific continuous vectors to guide program generation towards the given property, without modifying the LM's weights. Our training procedure optimizes these continuous vectors by enforcing specialized loss terms on different regions of code, using a high-quality dataset carefully curated by us. Our extensive evaluation shows that SVEN is highly effective in achieving strong security control. For instance, a state-of-the-art CodeGen LM with 2.7B parameters generates secure code for 59.1% of the time. When we employ SVEN to perform security hardening (or adversarial testing) on this LM, the ratio is significantly boosted to 92.3% (or degraded to 36.8%). Importantly, SVEN closely matches the original LMs in functional correctness.