Academic Research Skills for Claude Code: research → write → review → revise → finalize

符合nature论文学术表达和科研绘图的Skill

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images …

This is the official repository for the ICLR 2025 accepted paper Badrobot: Manipulating Embodied LLMs in the Physical World.

ACL 2025 (Main) HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States

This is a repository for jailbreak attack and defense experiments

Jailbreak attacks detection tool for LLM based application

Code repository for CS5446 project exploring defenses against jailbreak attacks on large-language models it includes datasets, notebooks, model/steering scripts and validation routines to reproduce…

Codes for paper "SafeAgentBench: A Benchmark for Safe Task Planning of \\ Embodied LLM Agents"

A collection of Embodied AI datasets.

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

A lightweight library for large laguage model (LLM) jailbreaking defense.

A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models

Every practical and proposed defense against prompt injection.

Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"

Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)

[ICLR 2025] Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems

[Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

Focused on the safety and security of Embodied AI

Hidden backdoor attack on NLP systems

An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

Simple PyTorch implementations of Badnets on MNIST and CIFAR10.

Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and Privacy 2019.

The open-sourced Python toolbox for backdoor attacks and defenses.

大麦网抢票脚本

Yolo X, v3 ~ v12 and several Multi-Object Tracker(SORT, DeepSORT, ByteTrack, BoT-SORT, etc.) in MOT17 and VisDrone2019 Dataset. It uses a unified style and integrated tracker for easy embedding in …