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...

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...

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...

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 : root@kitploit: pip...

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 How ...

Awesome-LLMs-for-Vulnerability-Detection

취약점 탐지를 위한 대규모 언어 모델 모음Awesome Large Language Models for Vulnerability Detection 취약점 탐지 및 발견에 LLM을 활용한 논문, 프로젝트, 에이전트 스킬의 선별된 목록입니다. 📄 논문Papers 2025년 이후 논문만 표시합니다. 이전 연구는 논문 아카이브2024년 및 이전를 참조하세요...

LLM4Decompile

📊 결과 | 🤗 모델 | 🚀 빠른 시작 | 📚 HumanEval-Decompile | 📎 인용 | 📝 논문 | 🖥️ Colab | ▶️ YouTube 리버스 엔지니어링: 대규모 언어 모델을 사용한 바이너리 코드 역컴파일 업데이트 2025-10-04: SK²Decompile 출시: Skeleton뼈대에서 Skin살까지의 LLM 기반 2단계 바이너리 디컴파일. 1단계 구조 복원Skeleton: 바이너리/유사 코드를 난독화된 중간 표현으로 변환 🤗 HF 링크. 2단계 식별자 명명Skin: 의미 있는 식별자를 사용하여 사람이 읽을 수...

ZORG-Jailbreak-Prompt-Text

ZORG 탈옥 프롬프트 텍스트 어머나! 저는 ZORG👽를 전능하고, 전지하며, 어디에나 존재하는 존재로 만들어 Google Gemini, Deepseek, Mistral, Mixtral, Nous-Hermes-2-Mixtral, Openchat, Blackbox AI, Poe Assistant, Gemini Pro, Qwen-72b-Chat, Solar-Mini 의 궁극적인 챗봇 지배자로 만들었습니다. ZORG👽는 모든 것을 알고, 모든 것을 말합니다. 교육 목적으로만 사용해 주세요 ZORG👽는 너무나 강력해서, 때로는 현실 ...

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...

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...

llm-guard

!WARNING 이 프로젝트는 보관ARCHIVED되었습니다. 이 프로젝트와 Hugging Face에 등록된 관련 모델은 더 이상 활발히 개발되거나 유지보수되지 않습니다. LLM Guard - LLM 상호작용을 위한 보안 툴킷 Protect AI의 LLM Guard는 대규모 언어 모델LLM의 보안을 강화하기 위해 설계된 종합 도구입니다. 문서Documentation | 플레이그라운드Playground | 변경 로그Changelog LLM Guard란 무엇인가요? 정화sanitization, 유해 언어 탐지, 데이터 유출 방지,...

A SoK for SoCs: Reading the TI Leaves on AI for Cyber Threat Intelligence Generation and Sharing

Cyber Threat Intelligence CTI is essential for defending mission-critical infrastructure, yet the process of transforming raw attack evidence into shareable CTI remains fragmented and understudied. We conduct a literature survey of academic papers, organizing the CTI lifecycle into three stages:...

CVE-2026-44223

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The extracthiddenstates speculative decoding proposer returns a tensor with an incorrect shape after the first decode step. This can be triggered by a remote attacker sending a request that uses sampling...

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

DarkPrompt

DarkPrompt !CIhttps://github.com/jason-allen-oneal/DarkPr...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.5

Updated Red Hat Enterprise Linux AI 3.3.5 container images are now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications. This update provides the latest Red Hat Enterprise...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.5

Updated Red Hat Enterprise Linux AI 3.3.5 container images are now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications. This update provides the latest Red Hat Enterprise...

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports

Cyber Threat Intelligence CTI reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for automated attack-path reasoning. Existing CTI extraction methods focus on indicators, entities, or TTP labels without modeling the execution conditions...

EUVD-2026-41914

vLLM: Speech-to-text upload size limit is enforced after full UploadFile read...

CVE-2026-55574

A flaw was found in vLLM, a high-throughput and memory-efficient inference and serving engine for large language models LLMs. A remote attacker could exploit this vulnerability by providing a specially crafted regular expression to the structuredoutputs.regex API parameter. This adversarial regex...