Pinned Repositories
AD-Pentest-Notes
用于记录内网渗透(域渗透)学习 :-)
AutoDAN
The official implementation of our paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
awesome-cs-books
经典编程书籍大全，涵盖：计算机系统与网络、系统架构、算法与数据结构、前端开发、后端开发、移动开发、数据库、测试、项目与团队、程序员职业修炼、求职面试等
Bergeron
Research into how collaborative language models can result in more robust moral alignment.
Clip1
llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
llm-ad
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
llm-security
Dropbox LLM Security research code and results
llm_attack_defense_arena
ltroin's Repositories
ltroin/llm_attack_defense_arena
ltroin/Clip1
ltroin/llm-ad
ltroin/AutoDAN
The official implementation of our paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
ltroin/Bergeron
Research into how collaborative language models can result in more robust moral alignment.
ltroin/clip
ltroin/llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
ltroin/llm-attacks
Universal and Transferable Attacks on Aligned Language Models
ltroin/llm-security
Dropbox LLM Security research code and results
ltroin/codamosa
ltroin/CodeBERT-vulnerability-detection
This is a fork of CodeBERT to fine tune the UniXCoder on vulnerability detection
ltroin/DeepInception
[arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
ltroin/garak
LLM vulnerability scanner
ltroin/GEIA
Code for Findings-ACL 2023 paper: Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence
ltroin/gemini
Gemini is a modern LaTex beamerposter theme 🖼
ltroin/GPTFuzz
Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
ltroin/hard-prompts-made-easy
ltroin/Jailbreak_LLM
ltroin/Jailbreaking-Attack-against-Multimodal-Large-Language-Model
ltroin/lihang-code
《统计学习方法》的代码实现
ltroin/Multi-GNN
Multi-GNN architectures for Anti-Money Laundering.
ltroin/pal
PAL: Proxy-Guided Black-Box Attack on Large Language Models
ltroin/poster
ltroin/prompt-injection-defense
Fine-tuning base models to build robust task-specific models
ltroin/prompt-injection-interp
ltroin/representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
ltroin/RIPPLE_official
ltroin/TAP
TAP: An automated jailbreaking method for black-box LLMs
ltroin/Terraform-from-zero-to-hero-10-Lab-GCP-Infrastucture-as-Code
Terraform從零開始-10+實戰Lab打造GCP雲端自動化架構
ltroin/vec2text
utilities for decoding deep representations (like sentence embeddings) back to text