Related papers: Detection Made Easy: Potentials of Large Language …

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Large language models have shown good potential in supporting software development tasks. This is why more and more developers turn to LLMs (e.g. ChatGPT) to support them in fixing their buggy code. While this can save time and effort, many…

With the rapid evolution of large language models (LLMs), new and hard-to-predict harmful capabilities are emerging. This requires developers to be able to identify risks through the evaluation of "dangerous capabilities" in order to…

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…

In Ethereum, the practice of verifying the validity of the passed addresses is a common practice, which is a crucial step to ensure the secure execution of smart contracts. Vulnerabilities in the process of address verification can lead to…

Large language models (LLMs) have recently emerged as promising tools for augmenting Security Operations Center (SOC) workflows, with vendors increasingly marketing autonomous AI solutions for SOCs. However, there remains a limited…

Hardware verification is crucial in modern SoC design, consuming around 70% of development time. SystemVerilog assertions ensure correct functionality. However, existing industrial practices rely on manual efforts for assertion generation,…

Large Language Models (LLMs) have significantly advanced text understanding and generation, becoming integral to applications across education, software development, healthcare, entertainment, and legal services. Despite considerable…

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…

Software vulnerabilities can result in catastrophic cyberattacks that increasingly threaten business operations. Consequently, ensuring the safety of software systems has become a paramount concern for both private and public sectors.…

Automatically locating vulnerable statements in source code is crucial to assure software security and alleviate developers' debugging efforts. This becomes even more important in today's software ecosystem, where vulnerable code can flow…

Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored. Recent work suggests that both graph neural network (GNN)-based and…

Security analysts face increasing pressure to triage large and complex vulnerability backlogs. Large Language Models (LLMs) offer a potential aid by automating parts of the interpretation process. We evaluate four models (ChatGPT, Claude,…

Deep learning (DL) techniques are on the rise in the software engineering research community. More and more approaches have been developed on top of DL models, also due to the unprecedented amount of software-related data that can be used…

Background: Leaking sensitive information - such as API keys, tokens, and credentials - in source code remains a persistent security threat. Traditional regex and entropy-based tools often generate high false positives due to limited…

Large Language Models (LLMs) have emerged as a transformative and disruptive technology, enabling a wide range of applications in natural language processing, machine translation, and beyond. However, this widespread integration of LLMs…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

Smart contracts are self-executing programs that run on blockchains (e.g., Ethereum). 680 million US dollars worth of digital assets controlled by smart contracts have been hacked or stolen due to various security vulnerabilities in 2021.…

Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…