Aggregator
MOSEC会后随想:浏览器安全、web3钱包插件端安全
Client-Side Protection & Compliance: Fight Threats, Help Meet PCI DSS v4
图片验证码引起的惨案 一个开源验证码库导致的 jumpserver 账户接管漏洞
jumpserver 前不久出了一个密码重置漏洞 CVE-2023-42820
在当天我就复现了这个漏洞 这个随机数的案例非常有趣 这个漏洞出现在了一个很难想到的位置 是一个由第三方依赖库引起的问题
那些年我看过的番剧、电视剧、电影以及玩过的游戏
一些不错的作品值得更多的人接触,特此写下那些年我接触过的有趣的娱乐作品,我推荐的作品或是能让人获得新颖的体验,或是能让人思考良久,或是能让人轻松愉快。
<Kicking off NIST's Cybersecurity Awareness Month Celebration & Our Cybersecurity Awareness Month 2023 Blog Series
共济会最高揭秘
共济会最高揭秘
共济会最高揭秘
共济会最高揭秘
共济会最高揭秘
Introducing Sift: Automated Threat Hunting
业余无线电考试A、B操作证试题速记
有关业余无线电的碎碎念
HaE入门到精通:三条影响你一生的HaE规则
国庆快乐
A Closer Look at the Snatch Data Ransom Group
国庆快乐
Microsoft Fixes Data Exfiltration Vulnerability in Azure AI Playground
Large Language Model (LLM) applications and chatbots are quite commonly vulnerable to data exfiltration. In particular data exfiltration via Image Markdown Injection is quite frequent.
Microsoft fixed such a vulnerability in Bing Chat, Anthropic fixed it in Claude, and ChatGPT has a known vulnerability as Open AI “won’t fix” the issue.
This post describes a variant in the Azure AI Playground and how Microsoft fixed it.
From Untrusted Data to Data ExfiltrationWhen untrusted data makes it into the LLM prompt context it can instruct the model to inject an image markdown element. Clients frequently render this using an HTML img tag and if untrusted data is involved the attacker can control the src attribute.