AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization

arXiv:2402.11940v1 Announce Type: cross
Abstract: Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of CV and NLP is the problem of image captioning, where the related models' robustness against adversarial attacks has not been well studied. In this paper, we present a novel adversarial attack strategy, which we call AICAttack (Attention-based Image Captioning Attack), designed to attack image captioning models through subtle perturbations …

abstract advances adversarial adversarial attacks and natural language processing arxiv attacks attention captioning computer computer vision cs.cr cs.cv cs.lg deep learning image intersection language language processing natural natural language natural language processing nlp optimization processing research robustness tasks type vision