Fixing hardware security bugs with large language models

B Ahmad, S Thakur, B Tan, R Karri… - arXiv preprint arXiv …, 2023 - arxiv.org
Novel AI-based code-writing Large Language Models (LLMs) such as OpenAI's Codex have
demonstrated capabilities in many coding-adjacent domains. In this work we consider how …

On hardware security bug code fixes by prompting large language models

B Ahmad, S Thakur, B Tan, R Karri… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Novel AI-based code-writing Large Language Models (LLMs) such as OpenAI's Codex have
demonstrated capabilities in many coding-adjacent domains. In this work, we consider how …

The living review on automated program repair

M Monperrus - 2018 - hal.science
Concept This paper is a living review on automatic program repair 1. Compared to a
traditional survey, a living review evolves over time. I use a concise bullet-list style meant to …

Refining decompiled c code with large language models

WK Wong, H Wang, Z Li, Z Liu, S Wang, Q Tang… - arXiv preprint arXiv …, 2023 - arxiv.org
AC decompiler converts an executable into source code. The recovered C source code,
once re-compiled, is expected to produce an executable with the same functionality as the …

Decomperson: How humans decompile and what we can learn from it

K Burk, F Pagani, C Kruegel, G Vigna - 31st USENIX Security …, 2022 - usenix.org
Human analysts must reverse engineer binary programs as a prerequisite for a number of
security tasks, such as vulnerability analysis, malware detection, and firmware re-hosting …

[PDF][PDF] Ahoy sailr! there is no need to dream of c: A compiler-aware structuring algorithm for binary decompilation

ZL Basque, AP Bajaj, W Gibbs, J O'Kain… - Proceedings of the …, 2024 - usenix.org
Contrary to prevailing wisdom, we argue that the measure of binary decompiler success is
not to eliminate all gotos or reduce the complexity of the decompiled code but to get as close …

Exploring the Limits of ChatGPT in Software Security Applications

F Wu, Q Zhang, AP Bajaj, T Bao, N Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs) have undergone rapid evolution and achieved remarkable
results in recent times. OpenAI's ChatGPT, backed by GPT-3.5 or GPT-4, has gained instant …

Improving source-code representations to enhance search-based software repair

P Reiter, AM Espinoza, A Doupé, R Wang… - Proceedings of the …, 2022 - dl.acm.org
Automatically improving and repairing software using search-based methods is an active
research topic. Many current systems use existing source code as the ingredients of repairs …