Fooling Vision and Language Models Despite Localization and Attention Mechanism

Abstract: Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial examples for vision and LLMs, which incorporate natural language understanding and complex structures such as attention, localization, and modular architectures. In particular, we investigate attacks on a dense captioning model and on two visual question answering (VQA) models. Our evaluation shows that we can generate adversarial examples with a high success rate (i.e., > 90%) for these models. Our work sheds new light on understanding adversarial attacks on vision systems which have a language component and shows that attention, bounding box localization, and compositional internal structures are vulnerable to adversarial attacks. These observations will inform future work towards building effective defenses.