Awesome GitHub RepositoriesAdversarial Input Detection

Superagent is an AI safety platform that protects applications from prompt injections, data leaks, and harmful outputs through built-in guardrails. It functions as a prompt injection detection system, data redaction tool, and red team testing tool, automatically removing personally identifiable information and protected health data from AI inputs and outputs while scanning image uploads with vision AI to detect visual prompt injection attacks before processing. The platform routes every prompt through a sequential pipeline of safety checks including injection detection, data redaction, and co

NeMo-Guardrails is a toolkit for adding programmable safety constraints and dialogue boundaries to large language model conversational systems. It functions as security middleware that intercepts inputs and outputs to block prompt injections, jailbreaks, and sensitive data leaks, while providing a conversational dialogue manager to define structured interaction flows through configuration files. The framework includes a hallucination filter to screen model outputs for factual accuracy and a specialized modeling language for defining conversational flows and constraints. It provides capabiliti

The Adversarial Robustness Toolbox (ART) is an open-source library that provides a unified framework for evaluating, defending, and certifying machine learning models against adversarial threats. It wraps models from any framework behind a common estimator interface, enabling composable pipelines for attack generation, defense application, robustness certification, and privacy auditing across evasion, poisoning, and extraction threats. The library distinguishes itself by covering the full adversarial ML security lifecycle within a single toolkit. It supports gradient-based adversarial example

Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

agent-governance-toolkit este un framework pentru aplicarea politicilor de securitate, gestionarea identităților zero-trust și sandboxing-ul execuției agenților AI autonomi. Acesta oferă un strat de guvernanță conceput pentru a controla comportamentul agenților prin utilizarea unui motor de politici de securitate, gestionarea identității criptografice și un sandbox de execuție la runtime. Proiectul se distinge printr-un sistem de inele de privilegii pe mai multe niveluri și o rețea de identitate criptografică care securizează comunicarea între entitățile autonome. Implementează un mecanism de scor de încredere bazat pe degradare pentru a urmări fiabilitatea entității și utilizează jurnale de audit hash-chained, rezistente la manipulare, pentru a menține un istoric verificabil al execuției. Toolkit-ul acoperă o gamă largă de arii de capabilități, inclusiv securitatea prompt-urilor pentru a apăra împotriva atacurilor de injecție, maparea automată a conformității cu standardele de reglementare și orchestrarea fluxului de lucru autonom folosind tipare de tip saga. De asemenea, dispune de monitorizarea flotei pentru urmărirea sănătății și a limitelor de cheltuieli, precum și sandboxing-ul execuției instrumentelor pentru a restricționa accesul neautorizat la resurse. O interfață de linie de comandă este furnizată pentru executarea semnalelor de control, validarea politicilor de guvernanță și gestionarea instalării extensiilor.

LLM Guard is a security firewall and guardrail framework designed to scan and sanitize inputs and outputs for large language models. It functions as a proxy gateway and security layer to block prompt injections, toxicity, and sensitive data leakage while ensuring that model interactions remain compliant with organizational policies. The system distinguishes itself through a modular scanner pipeline that utilizes local model orchestration to eliminate external network dependencies. It supports real-time security filtering via streaming chunk analysis and implements a fail-fast execution model