Alternatives and similar repositories for lm_risk_cards

Users that are interested in lm_risk_cards are comparing it to the libraries listed below

• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆113Updated last year
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆23Updated last year
• lakeraai / pint-benchmark
  A benchmark for prompt injection detection systems.
  ☆124Updated 3 weeks ago
• briland / LLM-security-and-privacy
  LLM security and privacy
  ☆49Updated 9 months ago
• andyzorigin / cybench
  ☆130Updated last month
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆226Updated last week
• deadbits / vigil-llm
  ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
  ☆402Updated last year
• vinusankars / BEAST
  Implementation of BEAST adversarial attack for language models (ICML 2024)
  ☆90Updated last year
• liu00222 / Open-Prompt-Injection
  This repository provides a benchmark for prompt Injection attacks and defenses
  ☆255Updated 3 weeks ago
• LostOxygen / llm-confidentiality
  Whispers in the Machine: Confidentiality in Agentic Systems
  ☆39Updated 2 months ago
• precize / Agentic-AI-Top10-Vulnerability
  Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work
  ☆124Updated last month
• dropbox / llm-security
  Dropbox LLM Security research code and results
  ☆231Updated last year
• pasquini-dario / LLMmap
  ☆51Updated 2 weeks ago
• mitre-atlas / atlas-data
  ATLAS tactics, techniques, and case studies data
  ☆77Updated 3 months ago
• IBM / URET
  Universal Robustness Evaluation Toolkit (for Evasion)
  ☆31Updated 3 months ago
• microsoft / BIPIA
  A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.
  ☆73Updated last year
• mnns / LLMFuzzer
  🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …
  ☆303Updated last year
• trailofbits / awesome-ml-security
  ☆139Updated 2 months ago
• protectai / nbdefense
  Secure Jupyter Notebooks and Experimentation Environment
  ☆78Updated 6 months ago
• agencyenterprise / PromptInject
  PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…
  ☆401Updated last year
• kenhuangus / Top-Threats-for-AI-Agents
  ☆53Updated 3 months ago
• wearetyomsmnv / Awesome-LLMSecOps
  LLM | Security | Operations in one github repo with good links and pictures.
  ☆35Updated 7 months ago
• tldrsec / prompt-injection-defenses
  Every practical and proposed defense against prompt injection.
  ☆503Updated 5 months ago
• ZenGuard-AI / fast-llm-security-guardrails
  The fastest Trust Layer for AI Agents
  ☆140Updated 2 months ago
• HumanCompatibleAI / tensor-trust
  A prompt injection game to collect data for robust ML research
  ☆62Updated 6 months ago
• uiuc-kang-lab / InjecAgent
  ☆70Updated last year
• Reapor-Yurnero / imprompter
  Codebase of https://arxiv.org/abs/2410.14923
  ☆49Updated 9 months ago
• Libr-AI / OpenRedTeaming
  Papers about red teaming LLMs and Multimodal models.
  ☆131Updated 2 months ago
• AIM-Intelligence / Automated-Multi-Turn-Jailbreaks
  ☆82Updated 8 months ago
• sunblaze-ucb / cybergym
  CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…
  ☆49Updated last week