Should Generative AIs Have Safeguards?

Romain Aviolat, CISO of Kudelski Security, shares his thoughts on Llama Guard and explains why, for cybersecurity reasons, companies developing LLMs should simultaneously implement safeguards to prevent the generation of insecure AI code and minimize their utility to cyber adversaries. (iStock)

With the development and increasing use of generative AIs, should safeguards also be developed? Last December, Meta launched Llama Guard, a security tool that classifies the safety of LLM prompts and responses, using a taxonomy of risks. Romain Aviolat, CISO of Kudelski Security, shares his thoughts on Llama Guard and more generally how such tools … Continue reading Should Generative AIs Have Safeguards?

DirectIndustry e-Magazine
0 Comments