Labels Predicted by AI
悪意のあるプロンプト インダイレクトプロンプトインジェクション 敵対的サンプル
Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.
Abstract
We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an image or audio recording. When the user asks the (unmodified, benign) model about the perturbed image or audio, the perturbation steers the model to output the attacker-chosen text and/or make the subsequent dialog follow the attacker’s instruction. We illustrate this attack with several proof-of-concept examples targeting LLaVa and PandaGPT.