AI
【顶会论文分享】OWAD：应对正常数据漂移的通用框架
一. 前言概念漂移是基于学习的安全应用程序所面临的挑战之一，通常这些应用程序建立在训练和部署分布相同的封闭世界假设之上。对于数据的漂移，现有研究主要...
AI供应链安全：Hugging Face 恶意ML模型事件分析
01 Hugging Face供应链攻击事件分析事件背景近期由JFrog安全团队监控发现，Hugging Face平台上的某些机器学习模型可能被用于对用户环境进行攻击。这些恶意的...
Web LLM Attacks
The integration of Large Language Models (LLMs) into online platforms presents a double-edged sword, offering enhanced user experiences but also in...
【中科院计算所】WSDM 2024冠军方案：基于大模型进行多文档问答
作者：李一鸣 张兆 中科院计算所会话式多文档问答旨在根据检索到的文档以及上下文对话来回答特定问题。在本文中，我们介绍了 WSDM Cup 2024 中“对话式多文档 ...
AIGC产品内容安全测试浅析
点击蓝字 关注我们AIGC产品内容安全测试浅析引言AIGC（Artificial Intelligence Generated Content，生成式人工智能）技术，依托生成对抗网络、大型预训练模...
Data Scientists Targeted by Malicious Hugging Face ML Models with Silent Backdoor
In the realm of AI collaboration, Hugging Face reigns supreme. But could it be the target of model-based attacks? Recent JFrog findings suggest a c...
SecGPT-Mini的一些补充
现在每个人都可以在电脑内置一个10年经验的安全专家了。SecGPT-Mini：是一个可以在普通CPU上运行的网络安全大模型。对昨天 https://mp.weixin.qq.com/s?__biz...
Analyzing AI Application Threat Models
Abstract 摘要 The following analysis explores the paradigm and security implications of machine learning integration into application architectures...
2024 DevSecOps Predictions – Part 1
DEVOPSdigest asked industry experts how they think DevSecOps will evolve and impact development and application security in 2024. DEVOPSdigest询问...
2024 DevSecOps Predictions – Part 2
DEVOPSdigest asked industry experts how they think DevSecOps will evolve and impact development and application security in 2024. Part 2 covers ris...