t0hka's starred repositories
active-learning
Continuous Learning for Android Malware Detection (USENIX Security 2023)
multilingual-safety-for-LLMs
[ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"
EasyJailbreak
An easy-to-use Python framework to generate adversarial jailbreak prompts.
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
SafeDecoding
Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
cross-inlining_binary_function_similarity
The repository of the paper "Cross-Inlining Binary Function Similarity Detection"
awesome-ml-privacy-attacks
An awesome list of papers on privacy attacks against machine learning
Open-Sora-Plan
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
llm-paper-daily
Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个
Chat-Haruhi-Suzumiya
Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.
ChatGLM-Finetuning
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
awesome-adversarial-examples-dl
A curated list of awesome resources for adversarial examples in deep learning
Awesome-Malware-Related-Papers
A curated list of malware-related papers.
Anti-Disassembly-On-Arm64
User inline asm to anti-disassembly on arm64
AndroidChecklist
Android应用审计checklist整理
android-inline-hook
:fire: ShadowHook is an Android inline hook library which supports thumb, arm32 and arm64.