Human developers can produce code with cybersecurity bugs. Can emerging 'smart'code completion tools help repair those bugs? In this work, we examine the use of large language …
Machine Learning (ML) represents a pivotal technology for current and future information systems, and many domains already leverage the capabilities of ML. However, deployment …
J Willbold, M Schloegel, M Vögele… - … IEEE Symposium on …, 2023 - ieeexplore.ieee.org
Satellites are an essential aspect of our modern society and have contributed significantly to the way we live today, most notable through modern telecommunications, global positioning …
The increasing cost of successful cyberattacks has caused a mindset shift, whereby defenders now employ proactive defenses, namely software bug hunting, alongside existing …
More and more Android apps implement their functionalities in native code, so does malware. Although various approaches have been designed to analyze the native code …
Critical software is written in memory unsafe languages that are vulnerable to use-after-free and double free bugs. This has led to proposals to secure memory allocators by strategically …
J Zeng, C Zhang, Z Liang - Proceedings of the 2022 ACM SIGSAC …, 2022 - dl.acm.org
System auditing is the foundation of attack provenance to investigate root causes and ramifications of cyber-attacks. However, provenance tracking on coarse-grained audit logs …
Understanding the cause, consequences, and severity of a security bug are critical facets of the overall bug triaging and remediation process. Unfortunately, diagnosing failures is often …
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 …