Alternatives and similar repositories for BEAST-implementation

Users that are interested in BEAST-implementation are comparing it to the libraries listed below

• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆117Updated 2 years ago
• NickNameInvalid / LLM_CTF
  ☆66Updated 4 months ago
• dreadnode / research
  General research for Dreadnode
  ☆27Updated last year
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆112Updated last year
• vinusankars / BEAST
  Implementation of BEAST adversarial attack for language models (ICML 2024)
  ☆90Updated last year
• wunderwuzzi23 / token-turbulenz
  ☆29Updated 2 years ago
• haizelabs / get-haized
  A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.
  ☆100Updated 9 months ago
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆65Updated last year
• dreadnode / example-agents
  Example agents for the Dreadnode platform
  ☆22Updated last month
• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆250Updated 11 months ago
• trailofbits / pajaMAS
  Multi-agent system (MAS) hijacking demos
  ☆40Updated this week
• google-research / camel-prompt-injection
  Code for the paper "Defeating Prompt Injections by Design"
  ☆246Updated 7 months ago
• dreadnode / paperstack
  Arxiv + Notion Sync
  ☆20Updated 8 months ago
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆68Updated 11 months ago
• redteaming-arena / redteam-arena
  ☆38Updated 8 months ago
• HKU-TASR / Imperio
  [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…
  ☆44Updated 11 months ago
• evilsocket / mini-rag
  A simple, 100% Rust implementation of a vector storage database with on disk persistency.
  ☆31Updated last year
• trailofbits / CompChomper
  CompChomper is a framework for measuring how LLMs perform at code completion.
  ☆19Updated 9 months ago
• controllability / jailbreak-evaluation
  The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.
  ☆27Updated last year
• PalisadeResearch / intercode
  https://arxiv.org/abs/2412.02776
  ☆67Updated last year
• PromptDefender / PromptDefender
  A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks.
  ☆21Updated last month
• 5stars217 / malicious_models
  using ML models for red teaming
  ☆45Updated 2 years ago
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆53Updated last year
• AlignmentResearch / gpt-4-novel-apis-attacks
  ☆23Updated 2 years ago
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆134Updated this week
• JosephTLucas / vger
  An interactive CLI application for interacting with authenticated Jupyter instances.
  ☆55Updated 9 months ago
• Reapor-Yurnero / imprompter
  Codebase of https://arxiv.org/abs/2410.14923
  ☆54Updated last year
• haizelabs / thorn-in-haizestack
  Thorn in a HaizeStack test for evaluating long-context adversarial robustness.
  ☆26Updated last year
• dreadnode / robopages
  A YAML based format for describing tools to LLMs, like man pages but for robots!
  ☆84Updated 9 months ago
• StavC / Here-Comes-the-AI-Worm
  Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems
  ☆222Updated 5 months ago