1
安全公司曝光黑客利用 AI 打造模块化恶意框架 Avalon，可按需加载各种组件
上传文件或链接即可扫描恶意软件，集成70+反病毒引擎，实时检测威胁。
IT之家 7 月 7 日消息，安全公司 Blackpoint 发文，透露近期市面上出现一款名为 Avalon 的模块化恶意框架，相应框架系黑客利用 AI 打造而成。 研究人员表示，过去黑客利用 AI 生成的恶意软件多半局限于后门、勒索工具或信息窃取脚本等单一类型；而 Avalon 则属于整合多种攻击…
2
Symfony: Validating & Secure your API Requests
一篇让Symfony开发者瞬间提升API安全性的实战指南，7分钟教会你用#[MapRequestPayload]优雅搞定验证与防护。
When you build an API, the first line of defense isn't your firewall or your database — it's the request itself. Every payload that hits your controll…
3
AI Surveillance: Age Verification Meets Your Chat Logs
AI时代隐私保护利器，自动检测年龄验证请求并分析聊天记录风险，支持一键举报违规行为，守护你的数字身份。
Article URL: https://techtrenches.dev/p/the-cost-of-reading-everyone-just Comments URL: https://news.ycombinator.com/item?id=48678388 Points: 2 # Comm…
4
Build a Basic AI Agent from Scratch: Human in the Loop and Security
从零构建AI Agent，详解人机回环与安全机制，附完整代码实战
Article URL: https://www.ruxu.dev/articles/ai/build-an-ai-agent-human-in-the-loop-security/ Comments URL: https://news.ycombinator.com/item?id=4857037…
5
Valta: We built hard spending limits that AI agents cannot break
AI代理不再超支！Valta给开发者提供无法被突破的硬性支出限制，精准控制成本
Hey Dev, I built the first tool that gives developers hard spending limits inside AI agents — instead of reactive account-level caps that only kick in…
6
SV-Detect: AI-generated Text Detection with Steering Vectors
用转向向量（Steering Vectors）精准识别AI生成文本，为深度伪造检测提供新思路。
arXiv:2606.07313v1 Announce Type: cross Abstract: Detecting machine-generated text is especially difficult under distribution shift, such as transfer …
7
Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs
一种零样本的LLM提示注入防御方法，通过检测嵌入漂移实现轻量级保护，已被NeurIPS研讨会接收。
arXiv:2601.12359v1 Announce Type: cross Abstract: Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversa…
8
安全公司警告有黑客在 GitHub 利用自动安装脚本发起供应链投毒，超 700 个代码库遭污染
Socket Security实时监控开源依赖中的恶意行为，尤其能发现Postinstall自动安装脚本投毒，保护供应链安全
IT之家 6 月 7 日消息，网络安全公司 Socket 研究团队发文，透露有黑客利用“Postinstall”自动安装脚本发起供应链攻击，目前已污染超过 700 个 GitHub 公开代码库。 Socket 表示，黑客在此次攻击事件中首先对 GitHub 多个上游代码仓库动手，悄悄修改 packa…
9
Google’s June Android Drop Could End AI Scam Calls for Good
Google新功能用发出“询问”指令，让AI诈骗电话原形毕露，守护你的钱袋子。
Plus, upgrades for Circle to Search, Google Photos, and Emoji Kitchen.
10
Google rolls out fake call detection to protect against AI deepfake impersonation scams
Google推出假电话检测，实时识别AI深度伪造冒充诈骗，保护通话安全
As people increasingly refuse to answer calls from unknown numbers, scammers are shifting their tactics by spoofing trusted phone numbers and using AI…
11
How to protect your AI endpoints with Vercel BotID
Vercel BotID 教你三步防护 AI 端点，轻松应对 3000% 流量暴增
Article URL: https://vercel.com/kb/guide/protect-ai-endpoints-with-vercel-botid Comments URL: https://news.ycombinator.com/item?id=48342146 Points: 2 …
12
AiLock: Hide source from AI assistants while tests still run
加密代码防AI读取，内存解密不干扰运行，开源神器AiLock让AI助手无从下手
Article URL: https://github.com/lo2589/AILOCK Comments URL: https://news.ycombinator.com/item?id=48345582 Points: 1 # Comments: 0
13
AI安全网关：企业统一接入、安全防护与数据安全的必要性与实践路径
企业员工用AI引发数据泄露危机，AI安全网关如何统一接入、防护并合规？
14
Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
LLM安全新防线：让模型通过逻辑自省识别并抵御对抗提示攻击
arXiv:2605.24834v1 Announce Type: cross Abstract: Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly…
15
阻止逾 22 亿美元潜在欺诈交易，苹果公布 App Store 2025 年安全防护成绩单
苹果 App Store 2025 年安全成绩单出炉：阻止超 22 亿美元欺诈、驳回 200 万款问题应用，审核强度惊人。
IT之家 5 月 20 日消息，在下月苹果年度开发者大会召开前夕，苹果分享了一份最新报告，介绍了 App Store 如何依托多重防护机制，同时服务广大用户与开发者群体。 苹果详细阐述了其为防范各类侵害行为、保障用户及开发者权益所采取的各项措施。官方称，App Store 早已成为全球性平台，每周有…
16
Aperion Shield: local guardrail that blocks destructive AI coding agent ops
开源本地安全护栏，阻挡AI编码代理的破坏性操作，v0.7新增45+自适应规则与更多测试用例。
Article URL: https://github.com/AperionAI/shield Comments URL: https://news.ycombinator.com/item?id=48207471 Points: 2 # Comments: 0