[1]
Yin, Z. et al. 2024. VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models. Proceedings of the AAAI Conference on Artificial Intelligence. 38, 7 (Mar. 2024), 6755–6763. DOI:https://doi.org/10.1609/aaai.v38i7.28499.