Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space
Current research in adversarial robustness of LLMs focuses on discrete input manipulations
in the natural language space, which can be directly transferred to closed-source models …
in the natural language space, which can be directly transferred to closed-source models …
Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation
Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models
to real-world systems. Adversarial training has proven to be one of the most promising …
to real-world systems. Adversarial training has proven to be one of the most promising …