safellama / plexiglass

Related projects: ⓘ

• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆116Updated 5 months ago
• mik0w / pallms
  Payloads for Attacking Large Language Models
  ☆56Updated 2 months ago
• lve-org / lve
  A repository of Language Model Vulnerabilities and Exposures (LVEs).
  ☆103Updated 6 months ago
• fiddler-labs / fiddler-auditor
  Fiddler Auditor is a tool to evaluate language models.
  ☆163Updated 6 months ago
• deadbits / vigil-llm
  ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
  ☆299Updated 7 months ago
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
  ☆181Updated last month
• dropbox / llm-security
  Dropbox LLM Security research code and results
  ☆210Updated 3 months ago
• corca-ai / LLMFuzzAgent
  [Corca / ML] Automatically solved Gandalf AI with LLM
  ☆46Updated last year
• lakeraai / pint-benchmark
  A benchmark for prompt injection detection systems.
  ☆80Updated last week
• leondz / lm_risk_cards
  Risks and targets for assessing LLMs & LLM vulnerabilities
  ☆24Updated 3 months ago
• mithril-security / blindbox
  BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps
  ☆57Updated 10 months ago
• JosephTLucas / jupysec
  A JupyterLab extension to evaluate the security of your Jupyter environment
  ☆36Updated last year
• mrwadams / honeyagents
  HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …
  ☆34Updated 8 months ago
• haizelabs / get-haized
  A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.
  ☆77Updated 3 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…
  ☆293Updated 6 months ago
• dreadnode / rigging
  Lightweight LLM Interaction Framework
  ☆181Updated this week
• StavC / ComPromptMized
  ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications
  ☆189Updated 6 months ago
• invariantlabs-ai / invariant
  A trace analysis tool for AI agents.
  ☆97Updated this week
• hwchase17 / adversarial-prompts
  Curation of prompts that are known to be adversarial to large language models
  ☆170Updated last year
• unica-mlsec / mlsec
  PhD/MSc course on Machine Learning Security (Univ. Cagliari)
  ☆190Updated this week
• briland / LLM-security-and-privacy
  LLM security and privacy
  ☆38Updated 5 months ago
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆41Updated 4 months ago
• protectai / modelscan
  Protection against Model Serialization Attacks
  ☆273Updated this week
• subzer0girl2 / AI-Threat-Mind-Map
  ☆15Updated 4 months ago
• llmsecnet / llmsec-site
  source for llmsec.net
  ☆11Updated last month
• ottosulin / awesome-ai-security
  A collection of awesome resources related AI security
  ☆107Updated 5 months ago
• RiccardoBiosas / awesome-MLSecOps
  A curated list of MLSecOps tools, articles and other resources on security applied to Machine Learning and MLOps systems.
  ☆220Updated last month
• vinusankars / BEAST
  Implementation of BEAST adversarial attack for language models (ICML 2024)
  ☆72Updated 4 months ago
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆15Updated last year
• mitre-atlas / ai-risk-database
  Explore AI Supply Chain Risk with the AI Risk Database
  ☆44Updated 4 months ago