CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks
AiScan-N Lai Liao !Zhe Shi Yi Kuan Ji Yu Ren Gong Zhi Neng Qu Dong De AiZi Dong Hua Wang Luo An Quan (Yun Wei )Gong Ju ,Zhuan Zhu Yu Wang Luo An Quan Ping Gu , Lou Dong Sao Miao , Yun Wei , Ying Ji Xiang Ying , Shen Tou Ce Shi Zi Dong Hua ,AiDa Mo Xing Gong Ju Ji [(CLI Agent)] ,AiQu Dong De An Quan Jian Ce Ji Zhu ,Ti Sheng An Quan Ce Shi (Yun Wei )Xiao Lu ,Zhuan Wei Qi Ye He Ge Ren Yong Hu Da Zao ,You Qi Gua He Chu Xue Zhe (Xiao Bai )Kuai Su Shang Shou Shi Yong ,Rang Ni Qing Song Mai Ru Zhi Neng An Quan Gong Fang Shi Dai !Gua Yong Chang Jing :Ru (Hong Dui Yan Lian , CTFBi Sai , WebYing Yong Shen Tou Ce Shi , Nei Wang Heng Xiang Yi Dong , Mi Ma Po Jie Yu Bao Li Gong Ji , Liu Liang Fen Xi Yu Wei Xie Jian Ce , APTGong Ji Mo Ni , Lou Dong Shang Jin Tiao Zhan Deng Chang Jing )Yan Shi Shi Pin (Wen Zhang Zhong ):https://mp.weixin.qq.com/s/7lsUdbrxkDy4P5pZhEWv7Q
Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems
CTF challenges designed and implemented in machine learning applications
Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.
AI runtime inventory: discover shadow AI, trace LLM calls
A collection list for Large Language Model (LLM) Watermark
An interactive CLI application for interacting with authenticated Jupyter instances.
Yi Kuan Ji He Liao Chang Jian De Lou Dong Lian Xi Ping Tai ,Li Yong AiDui Ba Chang Jin Xing Zi Dong Hua Shen Tou Ce Shi !
Powerful LLM Query Framework with YAML Prompt Templates. Made for Automation
[COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
A hybrid AI honeypot for monitoring large scale web attacks
CyberBrain_Model is an advanced AI project designed for fine-tuning the model `DeepSeek-R1-Distill-Qwen-14B` specifically for cyber security tasks.
AI Security EXPOSED! Live Demos Showing Hidden Risks of Agentic AI Flows: Prompt Injection, Data Poisoning. Watch the recorded session:
Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024
This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.
This repository is for Red Teamers, security researchers, AI enthusiasts, and students to learn about adversarial attacks on AI/LLM systems. It is strictly for educational use, and the authors disclaim responsibility for any misuse.
It is a pure front-end tool for testing the security boundaries of large language models, helping researchers to find and fix potential security vulnerabilities and improve the security and reliability of AI systems.
CyberBrain is an advanced AI project designed specifically for training artificial intelligence models on devices with limited hardware capabilities.
An intentionally vulnerable AI chatbot to learn and practice AI Security.
Add a description, image, and links to the aisecurity topic page so that developers can more easily learn about it.
To associate your repository with the aisecurity topic, visit your repo's landing page and select "manage topics."