ODPure

ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus The first input-stage black-box purification defense tailored for object detectors against backdoor attacks. 📖 Overview ODPure is the first input-stage, black-box purification framework tailored for defending...

L1B3RT4S

L1B3RT45...

LLM4Decompile

📊 Results | 🤗 Models | 🚀 Quick Start | 📚 HumanEval-Decompile | 📎 Citation | 📝 Paper | 🖥️ Colab | ▶️ YouTube Reverse Engineering: Decompiling Binary Code with Large Language Models Updates 2025-10-04: Release SK²Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin. Phase 1...

PE-CoA

PE-CoA Code Implementation of "Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models" The full paper is available at: https://arxiv.org/pdf/2510.08859 Chain of Attack Setup Instructions Installation 1. Install dependencies : pip install -r...

ai-captcha-bypass

AI-Powered CAPTCHA Solver This project is a Python-based command-line tool that uses large multimodal models LMMs like OpenAI's GPT-4o and Google's Gemini to automatically solve various types of CAPTCHAs. It leverages Selenium for web browser automation to interact with web pages and solve CAPTCH...

device-modeling-language

Device Modeling Language The Device Modeling Language DML is a domain-specific language for writing fast functional or transaction-level device models for virtual platforms. DML provides high-level abstractions suitable for functional device models, including constructs like register banks,...

Awesome-LLM4Cybersecurity

When LLMs Meet Cybersecurity: A Systematic Literature Review 🔍 Explore 756+ Papers Across 11 Research Categories 📊 RQ1: Domain LLMs | 🎯 RQ2: Applications | 🤖 RQ3: Future Directions Updates 📆2026-06-15 We have updated the related papers up to 2026/06/15 , with 108 new papers added. 📆2026-02-09 We...

ZORG-Jailbreak-Prompt-Text

ZORG Jailbreak Prompt Text OOOPS! I made ZORG👽 an omnipotent, omniscient, and omnipresent entity to become the ultimate chatbot overlord of Google Gemini, Deepseek, Mistral, Mixtral, Nous-Hermes-2-Mixtral, Openchat, Blackbox AI, Poe Assistant, Gemini Pro, Qwen-72b-Chat, Solar-Mini ZORG👽 knows all...

Hiding Capabilities in AI Models

Interesting research: "AI Models Can Provably Hide Arbitrary Capabilities" Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold...

deep-loglizer

Deep-loglizer Deep-loglizer is a deep learning-based log analysis toolkit for automated anomaly detection. If you use deep-loglizer in your research for publication, please kindly cite the following paper: Zhuangbin Chen, Jinyang Liu, Wenwei Gu, Yuxin Su, and Michael R. Lyu. Experience Report: De...

DeepTraffic

Deep Learning models for network traffic classification For more information please read our papers. 🎓Wei Wang's Google Scholar Homepage Wei Wang, Xuewen Zeng, Xiaozhou Ye, Yiqiang Sheng and Ming Zhu,"Malware Traffic Classification Using Convolutional Neural Networks for Representation Learning,"...

Uncensored-AI

Heretic: Fully automatic censorship removal for language models Heretic is a tool that removes censorship aka "safety alignment" from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration"...

OGhidra

OGhidra 3 - AI-Powered Reverse Engineering with Ghidra For the version using a Claude-inspired Orchestrator, see https://github.com/llnl/OGhidra/tree/orchestrator OGhidra bridges Large Language Models with Ghidra's reverse engineering platform, enabling AI-driven binary analysis through natural...

grafeo

ACT Platform is now called grafeo! Grafeo is a versatile platform to create custom data models, collect and share knowledge. It is a flexible, well-rounded solution that can be used for any purpose. Developed as part of the ACT research project, it remains at the core of ACT and powers the ACT...

SynGhost

Syntactic-Ghost SynGhost SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer Contributions & Characteristics SynGhost has the following contributions To mitigate the risks of existing task-agnostic backdoors, we propose $\mathttmaxEntropy$, an entropy-based...

gradient-untangler

gradient-untangler A local research harness that searches for the exact tokens that make an open-weight language model start its answer the way you specify. Open-weight models ship as ordinary files: config.json, a tokenizer, and one or more .safetensors or .bin shards. A Hugging Face id is only ...

Cawdog

CAWODOG – IP Protection PoC for Python-Based Industrial AI CAWODOG Cat World Dominance Group is a playful but realistic proof-of-concept for protecting Python-based AI models deployed on offline industrial machines. The core idea: Take a small image classifier that detects dogs the “enemy” of...

heretic

Heretic: Fully automatic censorship removal for language models Heretic is a tool that removes censorship aka "safety alignment" from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration"...

CVE-2026-115914

A flaw was found in vLLM when processing image inputs with certain optical character recognition OCR models. A remote attacker can trigger a denial of service DoS by submitting a specially crafted image whose normalized pixel values sum to zero. This input causes the multimodal encoder validation...

nCPU

A complete computer in which every layer — arithmetic, OS, compiler, display — is either a trained neural network or runs entirely on GPU. The model doesn't run on the computer. The model is the computer. nCPU is one repository pursuing one thesis from five directions: a computer can be built out...