The category you are using is not entirely suitable. Since Adversarial Robustness can be split into more detailed areas, like white-box jailbreaks, black-box jailbreaks, gradient-based jailbreaks, or red-LLM team jailbreaks. Don’t you think it would be better if you tagged them more subtly
The category you are using is not entirely suitable. Since Adversarial Robustness can be split into more detailed areas, like white-box jailbreaks, black-box jailbreaks, gradient-based jailbreaks, or red-LLM team jailbreaks. Don’t you think it would be better if you tagged them more subtly