Dual-Key Multimodal Backdoors for Visual Question Answering

被引：0
|
作者：
Walmer, Matthew [1 ]
Sikka, Karan [2 ]
Sur, Indranil [2 ]
Shrivastava, Abhinav [1 ]
Jha, Susmit [2 ]
机构：
[1] University of Maryland, College Park, United States
[2] SRI International, United States
来源：
arXiv | 2021年
关键词：
Backdoors - Multi-modal - Multimodal models - Multiple inputs - Non-trivial - Object detectors - Question Answering - Security vulnerabilities - Trojans - Visual feature;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [41] Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering
    Dancette, Corentin
    Cadene, Remi
    Teney, Damien
    Cord, Matthieu
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 1554 - 1563
  • [42] Graph-enhanced visual representations and question-guided dual attention for visual question answering
    Yusuf, Abdulganiyu Abdu
    Feng, Chong
    Mao, Xianling
    Haruna, Yunusa
    Li, Xinyan
    Duma, Ramadhani Ally
    NEUROCOMPUTING, 2025, 614
  • [43] Question Modifiers in Visual Question Answering
    Britton, William
    Sarkhel, Somdeb
    Venugopal, Deepak
    LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 1472 - 1479
  • [44] Multimodal Bi-direction Guided Attention Networks for Visual Question Answering
    Cai, Linqin
    Xu, Nuoying
    Tian, Hang
    Chen, Kejia
    Fan, Haodu
    NEURAL PROCESSING LETTERS, 2023, 55 (09) : 11921 - 11943
  • [45] DMRFNet: Deep Multimodal Reasoning and Fusion for Visual Question Answering and explanation generation
    Zhang, Weifeng
    Yu, Jing
    Zhao, Wenhong
    Ran, Chuan
    INFORMATION FUSION, 2021, 72 : 70 - 79
  • [46] RSMoDM: Multimodal Momentum Distillation Model for Remote Sensing Visual Question Answering
    Li, Pengfei
    Liu, Gang
    He, Jinlong
    Meng, Xiangxu
    Zhong, Shenjun
    Chen, Xun
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 16799 - 16814
  • [47] Medical Visual Question Answering Model Based on Knowledge Enhancement and Multimodal Fusion
    Dianyuan, Zhang
    Chuanming, Yu
    Data Analysis and Knowledge Discovery, 2024, 8 (8-9) : 226 - 239
  • [48] ViCLEVR: a visual reasoning dataset and hybrid multimodal fusion model for visual question answering in Vietnamese
    Tran, Khiem Vinh
    Phan, Hao Phu
    Van Nguyen, Kiet
    Nguyen, Ngan Luu Thuy
    MULTIMEDIA SYSTEMS, 2024, 30 (04)
  • [49] DMRFNet: Deep Multimodal Reasoning and Fusion for Visual Question Answering and explanation generation
    Zhang, Weifeng
    Yu, Jing
    Zhao, Wenhong
    Ran, Chuan
    Information Fusion, 2021, 72 : 70 - 79
  • [50] An Adaptive Multimodal Fusion Network Based on Multilinear Gradients for Visual Question Answering
    Zhao, Chengfang
    Tang, Mingwei
    Zheng, Yanxi
    Ran, Chaocong
    ELECTRONICS, 2025, 14 (01):
12345