相关论文: Harnessing LLMs for Document-Guided Fuzzing of Ope…

Fuzzing is one of the most effective technique to identify potential software vulnerabilities. Most of the fuzzers aim to improve the code coverage, and there is lack of directedness (e.g., fuzz the specified path in a software). In this…

LLM-based (Large Language Model) fuzz driver generation is a promising research area. Unlike traditional program analysis-based method, this text-based approach is more general and capable of harnessing a variety of API usage information,…

Database Management System (DBMS) is the key component for data-intensive applications. Recently, researchers propose many tools to comprehensively test DBMS systems for finding various bugs. However, these tools only cover a small subset…

Least-privilege separation decomposes applications into compartments limited to accessing only what they need. When compartmentalizing existing software, many approaches neglect securing the new inter-compartment interfaces, although what…

Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks either contain limited…

The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…

Open-source AI libraries are foundational to modern AI systems, yet they present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance. We introduce LibVulnWatch, a…

Deep learning (DL) has attracted wide attention and has been widely deployed in recent years. As a result, more and more research efforts have been dedicated to testing DL libraries and frameworks. However, existing work largely overlooked…

Developers utilize third-party libraries to improve productivity, which also introduces potential security risks. Existing approaches generate tests for public functions to trigger library vulnerabilities from client programs, yet they…

Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal inputs remains limited. In this work, we introduce VisCodex, a…

Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adopted in practice. However, previous work has shown that DL libraries, the basis of building and executing DL models, contain bugs and can…

Due to the impressive code comprehension ability of Large Language Models (LLMs), a few studies have proposed to leverage LLMs to locate bugs, i.e., LLM-based FL, and demonstrated promising performance. However, first, these methods are…

Large Language Models (LLMs) struggle with long-context code due to window limitations. Existing textual code compression methods mitigate this via selective filtering but often disrupt dependency closure, causing semantic fragmentation. To…

Testing a program's capability to effectively handling errors is a significant challenge, given that program errors are relatively uncommon. To solve this, Software Fault Injection (SFI)-based fuzzing integrates SFI and traditional fuzzing,…

Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

The Instruction Set Architecture (ISA) defines processor operations and serves as the interface between hardware and software. As an open ISA, RISC-V lowers the barriers to processor design and encourages widespread adoption, but also…

Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can…

The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for…

The proliferation of multimodal Large Language Models has significantly advanced the ability to analyze and understand complex data inputs from different modalities. However, the processing of long documents remains under-explored, largely…