Show HN: RedSOC – 100% prompt injection success on AI SoC assistantsgithub.com2 points·by krishna3145·قبل 3 أشهر·0 comments
krishna3145·قبل 3 أشهر·discusshttps://news.ycombinator.com/item?id=47916430 Check this out on LLMS security.
krishna3145·قبل 3 أشهر·discusshttps://www.researchgate.net/publication/403780821_Adversari...Show HN: RedSOC – adversarial evaluation framework for LLM-integrated SOCs