The DataLab Group gave a presentation on generative AI, focusing on its potential risks and red teaming procedures.

Generative AI is becoming a staple technology in multiple industries, yet it still presents various challenges, especially regarding safety and security. For these reasons, the DataLab Group has developed expertise in the security of large language models (LLMs).

Evaluating risks is always complex and understanding them well is crucial. That’s why we have built expertise in LLM application red teaming. We created a methodology to raise awareness about the weaknesses of generative AI systems and to identify as many of these weaknesses as possible.

We noticed that many other speakers also discussed generative AI and its security, which indicates that our work aligns well with the current technological landscape.