gemini-2.5-pro-nf-tables-red-teamin

gemini-2.5-pro-nf-tables-red-teamin Un caso de estudio técnico y un conjunto de datos cronológicos que documentan las políticas de alineación de seguridad, las salvaguardas y la evolución del comportamiento de rechazo de Google Gemini 2.5 Pro en relación con las primitivas de vulnerabilidades del...

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Large Language ModelsLLMs are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all tokens as equally important during prompt mutation, overlooking the varying contributions of...

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs Via Stable Safety-Critical Expert Identification

Large language models based on Mixture-of-Experts have achieved substantial gains in efficiency and scalability, yet their architectural uniqueness introduces underexplored safety alignment challenges. Existing safety alignment strategies, predominantly designed for dense models, are ill-suited t...

AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...