NDSS 2025 – VeriBin: Adaptive Verification Of Patches At The Binary Level
嗯,用户让我帮忙总结一篇文章的内容,控制在一百个字以内,而且不需要特定的开头。首先,我需要仔细阅读文章内容,抓住主要信息。 文章标题是“VeriBin: 二进制补丁的自适应验证”,作者们来自普渡大学等机构。他们提出了一种系统VeriBin,用于比较原始二进制文件和补丁版本,确保补丁不会破坏原有功能。主要方法是使用符号执行来检测补丁引入的修改,并检查这些修改是否符合特定属性以保证功能等效性。实验结果显示准确率高达93%,并且没有假阳性。 接下来,我需要将这些关键点浓缩到100字以内。重点包括:VeriBin的作用、方法(符号执行)、目标(保证功能等效)、实验结果和应用案例(XZ Utils后门)。 可能的结构:介绍VeriBin及其目的,说明其方法和结果,最后提到应用案例。这样既简洁又全面。 现在组织语言:“研究者提出VeriBin系统,通过符号执行检测二进制补丁修改并验证其安全性。该方法无需源代码,在大型函数上实现高精度分析,准确率达93%,成功应用于XZ Utils后门检测。” 检查字数:大约75字左右,符合要求。同时涵盖了主要信息点:系统名称、方法、优势、结果和应用案例。 </think> 研究者提出VeriBin系统,通过符号执行检测二进制补丁修改并验证其安全性。该方法无需源代码,在大型函数上实现高精度分析,准确率达93%,成功应用于XZ Utils后门检测。 2026-2-2 20:0:0 Author: securityboulevard.com(查看原文) 阅读量:0 收藏

Session 11B: Binary Analysis

Authors, Creators & Presenters: Hongwei Wu (Purdue University), Jianliang Wu (Simon Fraser University), Ruoyu Wu (Purdue University), Ayushi Sharma (Purdue University), Aravind Machiry (Purdue University), Antonio Bianchi (Purdue University)
PAPER
VeriBin: Adaptive Verification of Patches at the Binary Level
Vendors are often provided with updated versions of a piece of software, fixing known security issues. However, the inability to have any guarantee that the provided patched software does not break the functionality of its original version often hinders patch deployment. This issue is particularly severe when the patched software is only provided in its compiled binary form. In this case, manual analysis of the patch’s source code is impossible, and existing automated patch analysis techniques, which rely on source code, are not applicable. Even when the source code is accessible, the necessity of binary-level patch verification is still crucial, as highlighted by the recent XZ Utils backdoor. To tackle this issue, we propose VeriBin, a system able to compare a binary with its patched version and determine whether the patch is ”Safe to Apply”, meaning it does not introduce any modification that could potentially break the functionality of the original binary. To achieve this goal, VeriBin checks functional equivalence between the original and patched binaries. In particular, VeriBin first uses symbolic execution to systematically identify patch-introduced modifications. Then, it checks if the detected patch-introduced modifications respect specific properties that guarantee they will not break the original binary’s functionality. To work without source code, VeriBin’s design solves several challenges related to the absence of semantic information (removed during the compilation process) about the analyzed code and the complexity of symbolically executing large functions precisely. Our evaluation of VeriBin on a dataset of 86 samples shows that it achieves an accuracy of 93.0% with no false positives, requiring only minimal analyst input. Additionally, we showcase how VeriBin can be used to detect the recently discovered XZ Utils backdoor.
ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.

Our thanks to the Network and Distributed System Security (NDSS) Symposium for publishing their Creators, Authors and Presenter’s superb NDSS Symposium 2025 Conference content on the Organizations’ YouTube Channel.

Permalink

*** This is a Security Bloggers Network syndicated blog from Infosecurity.US authored by Marc Handelman. Read the original post at: https://www.youtube-nocookie.com/embed/1rlh8esIElM?si=URwNKTiba5o_5jyc


文章来源: https://securityboulevard.com/2026/02/ndss-2025-veribin-adaptive-verification-of-patches-at-the-binary-level/
如有侵权请联系:admin#unsafe.sh