Stars
A Diagnostic Guardrail Framework for AI Agent Safety and Security
An incremental parsing system for programming tools
[ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"
8-layer defense-in-depth security for agentic AI. Covers OWASP ASI Top 10 across ingestion, storage, context, planning, execution, output, inter-agent, and identity layers.
[ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.
[EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Progent: Securing AI Agents with Privilege Control
[NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents".
A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…
Every practical and proposed defense against prompt injection.
Code for the paper "Defeating Prompt Injections by Design"
Pip compatible CodeBLEU metric implementation available for linux/macos/win
Measuring the Mixing of Contextual Information in the Transformer
Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
🌎💪 BrowserGym, a Gym environment for web task automation
Search for papers by an author whose abstracts are most relevant to the keywords.
E-mails, subdomains and names Harvester - OSINT
A Multilingual Instruction Dataset on Code and trained on large language models.
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
A php cloaking script designed for use on Wordpress websites.