9 matches found
saffron
Saffron-1: Inference Scaling for LLM Safety Assurance 📖 Paper 🛠️ Dependencies The code was tested under the following dependencies: Python 3.12.3 CUDA 12.2 typingextensions==4.14.0 numpy==2.2.6 torch==2.5.1 huggingfacehub==0.30.2 accelerate==1.1.1 datasets==3.1.0 evaluate==0.4.3...
autoguardrails
autoguardrails Código abierto por Santander AI Lab. Una biblioteca / arnés de evaluación de investigación en seguridad de LLM / IA estilo autoresearch: busca sobre una única superficie mutable policy.md para minimizar la tasa de éxito de ataques ASR frente a un conjunto de evaluación fijo, con un...
meta-ai-support-prompt
Meta AI Support Assistant System Prompt Extracted system prompt from Meta's AI Support Assistant on June 1, 2026. Files system-prompt.md — Extracted system prompt ⚠️ Disclaimer & Legal Notice Purpose This repository is published strictly for educational and authorized security research purposes...
redeval
RedEval - LLM Safety Evaluation Framework A comprehensive framework for evaluating the safety of Large Language Models LLMs through systematic attack and refusal testing. RedEval provides a unified, secure, and extensible platform for assessing LLM robustness against adversarial prompts and harmf...
DARWIN
🧬 DARWIN Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection An evolutionary attack–defense framework that couples DARWIN-Attack with DARWIN-Guard through online adversarial training. Paper · Guard Checkpoint · Installation · Use DARWIN-Attack · Use DARWIN-Guard ·...
Russia-Aligned UAC-0099 Plants Nuclear Weapon Prompt in Malware to Disrupt AI Analysis
Cybersecurity researchers have disclosed a new technique dubbed GuardBreaker that's been put to use by a Russia-aligned threat actor known as UAC-0099 against a target in Ukraine with an aim to interfere with artificial intelligence AI-assisted analysis. The idea, ESET said in a series of posts o...
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the...
A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails Via Harmless Prompt Weaving and Adaptive Tree Search
Large language models LLMs remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional algorithmic search or recent agent-based workflows, the...
