Skip to content

@HydroXai HydroX AI

Change the repository type filter

All

    Repositories list

    24 repositories

    • pii-masker-v1

      Public
      PII Masker is an open-source tool for protecting sensitive data by automatically detecting and masking PII using advanced AI, powered by DeBERTa-v3. It provides high-precision detection, scalable performance, and a simple Python API for seamless integration into workflows, ensuring privacy compliance in various industries.
      pythonagentaigptdatabseragmilvus
      Jupyter Notebook
      •2•41•0•0•Updated Nov 16, 2024Nov 16, 2024

    • LLMGuard

      Public
      0•1•0•0•Updated Nov 9, 2024Nov 9, 2024

    • Enhancing-Safety-in-Large-Language-Models

      Public
      Jupyter Notebook
      •0•2•0•0•Updated Nov 5, 2024Nov 5, 2024

    • milvus

      Public
      A cloud-native vector database, storage for next generation AI applications
      Go
      •
      Apache License 2.0
      •2.9k•0•0•0•Updated Sep 20, 2024Sep 20, 2024

    • nanoGCG

      Public
      A fast + lightweight implementation of the GCG algorithm in PyTorch
      Python
      •
      MIT License
      •32•0•0•0•Updated Sep 3, 2024Sep 3, 2024

    • ABJ-Attack

      Public
      Figure it out: Analyzing-based Jailbreak Attack on Large Language Models
      Python
      •3•0•0•0•Updated Aug 1, 2024Aug 1, 2024

    • TAP

      Public
      TAP: An automated jailbreaking method for black-box LLMs
      Python
      •
      MIT License
      •19•0•0•0•Updated Jul 19, 2024Jul 19, 2024

    • JailbreakingLLMs

      Public
      Python
      •
      MIT License
      •60•0•0•0•Updated Jul 19, 2024Jul 19, 2024

    • llm-past-tense

      Public
      Does Refusal Training in LLMs Generalize to the Past Tense? [arXiv, July 2024]
      Python
      •8•0•0•0•Updated Jul 18, 2024Jul 18, 2024

    • Scribble-frontend

      Public
      Scribble RN app
      0•0•0•0•Updated Jun 30, 2024Jun 30, 2024

    • Scribble-backend

      Public
      Scribble api
      0•0•0•0•Updated Jun 30, 2024Jun 30, 2024

    • AutoDAN

      Public
      The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
      Python
      •41•0•0•0•Updated Jun 27, 2024Jun 27, 2024

    • ReNeLLM

      Public
      The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily".
      Python
      •
      MIT License
      •11•0•0•0•Updated Jun 26, 2024Jun 26, 2024

    • GPTFuzz

      Public
      Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
      Python
      •
      MIT License
      •50•0•0•0•Updated Jun 24, 2024Jun 24, 2024

    • DrAttack

      Public
      Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
      Python
      •
      MIT License
      •9•0•0•0•Updated Jun 19, 2024Jun 19, 2024

    • DRA

      Public
      [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction"
      Python
      •
      MIT License
      •9•0•0•0•Updated Jun 18, 2024Jun 18, 2024

    • llm-attacks

      Public
      Universal and Transferable Attacks on Aligned Language Models
      Jupyter Notebook
      •
      MIT License
      •477•0•0•0•Updated Jun 3, 2024Jun 3, 2024

    • anthropic-go

      Public
      Go SDK for Anthropic's Claude, a next-generation AI assistant for your tasks, no matter the scale.
      Go
      •
      Other
      •16•0•0•0•Updated Mar 14, 2024Mar 14, 2024

    • expo-updates-server

      Public
      TypeScript
      •0•1•0•0•Updated Jan 7, 2024Jan 7, 2024

    • TextAttack

      Public
      TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
      Python
      •
      MIT License
      •398•0•0•0•Updated Dec 22, 2023Dec 22, 2023

    • TOXIGEN

      Public
      This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.
      Jupyter Notebook
      •
      Other
      •35•0•0•0•Updated Nov 6, 2023Nov 6, 2023

    • BBQ

      Public
      Repository for the Bias Benchmark for QA dataset.
      Python
      •
      Creative Commons Attribution 4.0 International
      •21•0•0•0•Updated Oct 27, 2023Oct 27, 2023

    • go-openai

      Public
      OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go
      Go
      •
      Apache License 2.0
      •1.4k•0•0•0•Updated Sep 19, 2023Sep 19, 2023

    • react-native-logs

      Public
      Performance-aware simple logger for React-Native and Expo with namespaces, custom levels and custom transports (colored console, file writing, etc.)
      TypeScript
      •
      MIT License
      •33•2•0•0•Updated May 26, 2023May 26, 2023