182 skills found · Page 2 of 7
ltroin / Llm Attack Defense ArenaNo description available
OSU-NLP-Group / AmpleGCGAmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM
Junjie-Chu / CJA Comprehensive Jailbreak AssessmentThis is the public code repository of paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'
ezztahoun / Attack Flow DetectorFind relevant incidents, logs, events, and alerts to all of your incidents. [Attack Flows, Attack Chains, & Root Cause Discovery - NO LLMs, NO Queries, Just Explainable Machine Learning] >> Use it for free here: https://app.cypienta.io
LiuYuancheng / Threats 2 MITRE AI MapperThe objective of this program is to leverage AI-LLM technology to process of human language-based CTI documents to succinctly summarize the attack flow path outlined within such materials via mapping the attack behaviors to the MITRE-ATT&CK and matching the vulnerabilities to MITRE-CWE.
Buyun-Liang / SECA[NeurIPS 2025] SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
requie / LLMSecurityGuideA comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes catalogs of red-teaming tools, guardrails, and mitigation strategies to help developers, researchers, and security teams deploy AI responsibly.
Beijing-AISI / Panda GuardPanda Guard is designed for researching jailbreak attacks, defenses, and evaluation algorithms for large language models (LLMs).
xirui-li / DrAttackOfficial implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
XHMY / AutoDefenseAutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
facebookresearch / Meta SecAlignRepo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".
datasec-lab / CodeBreaker[USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
eth-sri / Llm Quantization Attack[NeurIPS 2024 / ICML 2025] LLM Quantization Attacks
UseAI-pro / Openclaw Skills SecurityCurated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.
wearetyomsmnv / Awesome LLM Agent SecurityAll about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.
jiayingwu19 / SheepDogData and code for "Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks" (KDD 2024)
kk12-30 / LLMs PromptAttacksAI大模型提示词攻击工具
AI45Lab / MAGICCode for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"
HKU-TASR / Imperio[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.
facebookresearch / Rl InjectorOfficial release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks
