Pinned Loading

1. advanced-web-agent-security advanced-web-agent-security Public

   A collection of research and engineering projects for securing LLM-based Web Agents against direct prompt injection, unauthorized actions, privacy violations, and excessive agency. Includes runtime…

   Python 1 3

2. Adv-AI-Agents Adv-AI-Agents Public

   A devel of production-grade Agentic AI systems including autonomous research agents, coding agents, RAG pipelines, and job search agents built with Python, LangChain, LangGraph, FAISS, and LLMs for…

   Python 4 4

3. RAI-RAG RAI-RAG Public

   Risk-Aware Introspective RAG (RAI-RAG) is a safety-aligned RAG framework integrating introspective reasoning, risk-aware retrieval gating, and secure evidence filtering to build trustworthy, robust…

   Python 1 1

4. Pre-Trained-Attacks Pre-Trained-Attacks Public

   A unified framework for covert backdoor and feature-based adversarial attacks on pre-trained encoders in self-supervised learning. Includes light/object/entity triggers, feature alignment attacks, …

   Python 1 3

5. BD-Attacks-Defenses BD-Attacks-Defenses Public

   A practical toolkit for implementing and evaluating backdoor attacks and defenses in deep learning. Includes BadNets, Blended attacks, and ShrinkPad defense. Ideal for researchers and students expl…

   Python 1 3

6. NLP-BD-Attacks NLP-BD-Attacks Public

   Analyzing backdoor attacks in Federated Learning systems focused on Natural Language Processing (NLP). Includes implementations of various attack strategies, model configurations, and evaluation sc…

   Python 2 3