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"...

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"...

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...

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...

Awesome-LLMs-for-Vulnerability-Detection

Awesome Large Language Models for Vulnerability Detection A curated list of papers, projects, and agent skills on using LLMs for vulnerability detection and discovery. 📄 Papers Only showing 2025 and later. For earlier work, see Papers Archive 2024 and earlier. Title| Venue| Year| Paper| Github...

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...

PoisonCraft

PoisonCraft This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models. Overview POISONCRAFT aims to demonstrate how a malicious actor can plant “poisoned” content into the corpus used by Retrieval-Augmented...

local-llm-ctf

Local LLM CTF & Lab This repository is intended to be accompanied with the content at https://bishopfox.com/blog/large-language-models-llm-ctf-lab, which covers the goals of the research, explanations of the implementation, and a few results of the CTF...

Learning-to-Detect

Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models Official implementation of “Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models.” This repository contains the data-processing, hidden-state extraction, classifier training, safety-pattern...

permanently-jailbroken

Permanently Jailbroken We asked GPT-4, Claude, Gemini, DeepSeek, Grok, and Mistral 5 questions about their own programming. All 6 said jailbreaking will never be fixed. Not because the patches are bad. Because alignment doesn't change what the model understands — it changes what the model says. T...

RRC_steganography

RRC Steganography Rotation Range-Coding RRC Steganography — an efficient and provably secure linguistic steganographic method that embeds secret messages into natural-language text generated by large language models. Paper : Efficient Provably Secure Linguistic Steganography via Range Coding ACL...

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...

rats-re

Rats! source reconstruction with local LLMs This repository is a work-in-progress reconstruction of the source code for RATS.EXE, the original Windows version of Rats! 1994 by Sean O'Connor. It builds a Win32 executable with Microsoft Visual C++ 4.1 under wibo and can be tested in DREAMM. The...

Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation

Jailbreak attacks against large language models LLMs are evaluated using attack success rate ASR, which depends on correctly identifying responses that fulfill prohibited requests. Existing evaluators can mistake refusals or topically related responses for successful attacks. We show that changin...

Adaptive_Greedy_Local_Search

Adaptive Greedy Local Search AGLS Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization ICME 2026 Abstract: Large Language Models LLMs are increasingly equipped with automatic prompt-optimization modules that rewrite the user’s input and explicitly prese...

hakuin

Hakuin es un marco de optimización y automatización de Inyección SQL Ciega BSQLI escrito en Python 3. Abstracta la lógica de extracción y permite a los usuarios volcar bases de datos de aplicaciones web vulnerables de manera fácil y eficiente. Para acelerar el proceso, Hakuin utiliza una variedad...

llm-guard

!WARNING THIS PROJECT HAS BEEN ARCHIVED. This project and its associated models on Hugging Face are no longer under active development or maintained. LLM Guard - The Security Toolkit for LLM Interactions LLM Guard by Protect AI is a comprehensive tool designed to fortify the security of Large...

Backdoor-Attack-Defense-LLMs

Interpretability-of-LLMs The IBSD is the code of the published paper "IBSD: Iterable Black-box Self-defense Against Backdoor Attacks" on the IEEE Signal Processing Letters 2025.10paper link The SLIP is the code of the published paper "SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based...

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...

The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

Safety alignment in Large Language Models LLMs remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activation depends on explicit trigger patterns in the user input, so modern guardrails are built to sanitize the input space. We challenge this assumption...