Related papers: An Empirical Study on Remote Code Execution in Mac…

$ $Large Language Models (LLMs) are being increasingly utilized in various applications, with code generations being a notable example. While previous research has shown that LLMs have the capability to generate both secure and insecure…

This paper presents a comprehensive empirical analysis of security vulnerabilities in AI-generated code across public GitHub repositories. We collected and analyzed 7,703 files explicitly attributed to four major AI tools: ChatGPT…

Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces…

Developing embedded systems is a complex endeavor that frequently requires collaborative teamwork. With the rise of freelance work and the global shift towards remote work, the need for effective remote collaboration has become crucial for…

The recent popularity of large language models (LLMs) has brought a significant impact to boundless fields, particularly through their open-ended ecosystem such as the APIs, open-sourced models, and plugins. However, with their widespread…

While Machine Learning (ML) technologies are widely adopted in many mission critical fields to support intelligent decision-making, concerns remain about system resilience against ML-specific security attacks and privacy breaches as well as…

Large Language Models (LLMs) have become powerful tools for automated code generation. However, these models often overlook critical security practices, which can result in the generation of insecure code that contains…

We analyzed nearly 460,000 AI model cards from Hugging Face to examine how developers report risks. From these, we extracted around 3,000 unique risk mentions and built the \emph{AI Model Risk Catalog}. We compared these with risks…

Qualitative data analysis is labor-intensive, yet the privacy risks associated with commercial Large Language Models (LLMs) often preclude their use in sensitive research. To address this, we introduce ChatQDA, an on-device framework…

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of…

Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL) imports annotated with specific version identifiers. These version choices can…

Performing deep learning on end-user devices provides fast offline inference results and can help protect the user's privacy. However, running models on untrusted client devices reveals model information which may be proprietary, i.e., the…

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To…

Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research environments (TREs) provide safe and secure environments in which researchers can…

The growth of cloud computing has revolutionized data processing and storage capacities to another levels of scalability and flexibility. But in the process, it has created a huge challenge of security, especially in terms of safeguarding…

LLM models are increasingly used to generate code, but the quality and security of this code are often uncertain. Several recent studies have raised alarm bells, indicating that such AI-generated code may be particularly vulnerable to…

The use of generative AI-based coding assistants like ChatGPT and Github Copilot is a reality in contemporary software development. Many of these tools are provided as remote APIs. Using third-party APIs raises data privacy and security…

Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in…

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) risks during model loading. Recent defenses, such as…

Trusted Execution Environments (TEEs) are a feature of modern central processing units (CPUs) that aim to provide a high assurance, isolated environment in which to run workloads that demand both confidentiality and integrity. Hardware and…