haizelabs / BEAST-implementation

Related projects ⓘ

Alternatives and complementary repositories for BEAST-implementation

• NickNameInvalid / LLM_CTF
  ☆61Updated 3 weeks ago
• dreadnode / tensor-man
  A utility to inspect, validate, sign and verify machine learning model files.
  ☆40Updated this week
• Mavenoid / prompt-hyperopt
  Improve prompts for e.g. GPT3 and GPT-J using templates and hyperparameter optimization.
  ☆41Updated last year
• dreadnode / parley
  Tree of Attacks (TAP) Jailbreaking Implementation
  ☆94Updated 9 months ago
• dreadnode / research
  General research for Dreadnode
  ☆17Updated 4 months ago
• haizelabs / thorn-in-haizestack
  Thorn in a HaizeStack test for evaluating long-context adversarial robustness.
  ☆26Updated 3 months ago
• haizelabs / get-haized
  A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.
  ☆85Updated 4 months ago
• cohere-ai / magikarp
  ☆127Updated last month
• for-ai / llm-profiling-toolkit
  ☆13Updated 4 months ago
• NYU-LLM-CTF / llm_ctf_automation
  ☆33Updated 2 weeks ago
• vinusankars / BEAST
  Implementation of BEAST adversarial attack for language models (ICML 2024)
  ☆72Updated 5 months ago
• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆142Updated 7 months ago
• invariantlabs-ai / invariant
  A trace analysis tool for AI agents.
  ☆118Updated 3 weeks ago
• timothee-chauvin / eyeballvul
  future-proof vulnerability detection benchmark, based on CVEs in open-source repos
  ☆44Updated last week
• andyzorigin / cybench
  ☆57Updated last week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆84Updated 8 months ago
• haizelabs / sphynx
  Sphynx Hallucination Induction
  ☆47Updated 3 months ago
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆17Updated last year
• moohax / Charcuterie
  Data Scientists Go To Jupyter
  ☆57Updated 2 years ago
• dreadnode / conferences
  ☆15Updated 6 months ago
• KhoomeiK / deredact
  De-redacting Elon's Email with Character-count Constrained Llama2 Decoding
  ☆10Updated 8 months ago
• chawins / pal
  PAL: Proxy-Guided Black-Box Attack on Large Language Models
  ☆46Updated 2 months ago
• AI-Voodoo / Red_Reaper_v2
  Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…
  ☆23Updated 2 months ago
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆106Updated 7 months ago
• JosephTLucas / vger
  An interactive CLI application for interacting with authenticated Jupyter instances.
  ☆49Updated 7 months ago
• user1342 / Oversight
  A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.
  ☆17Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆62Updated this week
• Cybonto / OllaDeck
  OllaDeck is a purple technology stack for Generative AI (text modality) cybersecurity. It provides a comprehensive set of tools for both …
  ☆13Updated last month
• VikParuchuri / classified
  Score LLM pretraining data with classifiers
  ☆55Updated last year
• mik0w / pallms
  Payloads for Attacking Large Language Models
  ☆62Updated 4 months ago