The red teaming exercise was conducted on several multimodal models, and tests across several safety and harm categories as described in the NIST AI RMF. Newer jailbreak techniques exploit the way multimodal models process combined media, bypassing content filters and leading to harmful outputs—without any obvious red flags in the visible prompt.

More info: https://www.enkryptai.com/company/resources/research-reports/mistral-pixtral-rt

#AISafety #LLMSecurity #RedTeaming #ModelRisk #CBRN #CSEM #VLM #AIAlignment #AIEthics #GenerativeAI #AICompliance #ResponsibleAI #enkryptai #enkrypt #AISecurity