相关论文: May the Feedback Be with You! Unlocking the Power …

Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like buffer overflows and use-after-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries such as…

Deep learning (DL) systems can make our life much easier, and thus are gaining more and more attention from both academia and industry. Meanwhile, bugs in DL systems can be disastrous, and can even threaten human lives in safety-critical…

Deep learning (DL) frameworks serve as the backbone for a wide range of artificial intelligence applications. However, bugs within DL frameworks can cascade into critical issues in higher-level applications, jeopardizing reliability and…

Detecting bugs in Deep Learning (DL) libraries (e.g., TensorFlow/PyTorch) is critical for almost all downstream DL systems in ensuring effectiveness/safety for end users. Meanwhile, traditional fuzzing techniques can be hardly effective for…

Deep Learning (DL) libraries such as PyTorch provide the core components to build major AI-enabled applications. Finding bugs in these libraries is important and challenging. Prior approaches have tackled this by performing either API-level…

DL frameworks are the basis of constructing all DL programs and models, and thus their bugs could lead to the unexpected behaviors of any DL program or model relying on them. Such a wide effect demonstrates the necessity and importance of…

Deep learning (DL) libraries are widely used in critical applications, where even subtle silent bugs can lead to serious consequences. While existing DL fuzzing techniques have made progress in detecting crashes, they inherently struggle to…

The widespread application of large language models (LLMs) underscores the importance of deep learning (DL) technologies that rely on foundational DL libraries such as PyTorch and TensorFlow. Despite their robust features, these libraries…

Fuzzing is an effective bug-finding technique but it struggles with complex systems like JavaScript engines that demand precise grammatical input. Recently, researchers have adopted language models for context-aware mutation in fuzzing to…

A growing body of research has been dedicated to DL model testing. However, there is still limited work on testing DL libraries, which serve as the foundations for building, training, and running DL models. Prior work on fuzzing DL…

Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I…

In this work, we set out to conduct the first ground-truth empirical evaluation of state-of-the-art DL fuzzers. Specifically, we first manually created an extensive DL bug benchmark dataset, which includes 627 real-world DL bugs from…

GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficiently by modeling operator parameters as formal constraints.…

As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a…

Jailbreak vulnerabilities in Large Language Models (LLMs), which exploit meticulously crafted prompts to elicit content that violates service guidelines, have captured the attention of research communities. While model owners can defend…

Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant…

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…

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars. It is of significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always…

Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs). Despite their potential, LLMs face specific challenges in fuzzing. In this paper, we identified five major challenges of…

Deep Learning (DL) library bugs affect downstream DL applications, emphasizing the need for reliable systems. Generating valid input programs for fuzzing DL libraries is challenging due to the need for satisfying both language…