Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks

被引：0
|
作者：
Hossain, Md Zarif [1 ,2 ]
Imteaj, Ahmed [1 ,2 ]
机构：
[1] Southern Illinois University, School of Computing, Carbondale,IL, United States
[2] Security, Privacy and Intelligence for Edge Devices Laboratory (SPEED Lab), United States
来源：
Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024 | 2024年
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Visual languages
引用
收藏
页码：6250 / 6259
相关论文
共 50 条
  • [31] VISION-LANGUAGE MODELS AS SUCCESS DETECTORS
    Du, Yuqing
    Konyushkova, Ksenia
    Denil, Misha
    Raju, Akhil
    Landon, Jessica
    Hill, Felix
    de Freitas, Nando
    Cabi, Serkan
    CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 232, 2023, 232 : 120 - 136
  • [32] Robust Calibration of Large Vision-Language Adapters
    Murugesan, Balamurali
    Silva-Rodriguez, Julio
    Ben Ayed, Ismail
    Dolz, Jose
    COMPUTER VISION - ECCV 2024, PT XXIV, 2025, 15082 : 147 - 165
  • [33] Securing Malware Cognitive Systems against Adversarial Attacks
    Ti, Yuede
    Bowman, Benjamin
    Huang, H. Howie
    2019 IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING (IEEE ICCC 2019), 2019, : 1 - 9
  • [34] Blind Adversarial Training: Towards Comprehensively Robust Models Against Blind Adversarial Attacks
    Xie, Haidong
    Xiang, Xueshuang
    Dong, Bin
    Liu, Naijin
    ARTIFICIAL INTELLIGENCE, CICAI 2023, PT II, 2024, 14474 : 15 - 26
  • [35] Adversarial Defense on Harmony: Reverse Attack for Robust AI Models Against Adversarial Attacks
    Kim, Yebon
    Jung, Jinhyo
    Kim, Hyunjun
    So, Hwisoo
    Ko, Yohan
    Shrivastava, Aviral
    Lee, Kyoungwoo
    Hwang, Uiwon
    IEEE ACCESS, 2024, 12 : 176485 - 176497
  • [36] Debiasing vision-language models for vision tasks: a survey
    Zhu, Beier
    Zhang, Hanwang
    FRONTIERS OF COMPUTER SCIENCE, 2025, 19 (01)
  • [37] Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks
    He, Xiang
    Yang, Sibei
    Li, Guanbin
    Li, Haofeng
    Chang, Huiyou
    Yu, Yizhou
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 8417 - 8424
  • [38] Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
    Li, Xiao
    Li, Zhuhong
    Li, Qiongxiu
    Lee, Bingze
    Cui, Jinghao
    Hu, Xiaolin
    arXiv,
  • [39] White-box Multimodal Jailbreaks Against Large Vision-Language Models
    Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China
    不详
    不详
    MM - Proc. ACM Int. Conf. Multimed., (6920-6928):
  • [40] HARNESSING TASK OVERLOAD FOR SCALABLE JAILBREAK ATTACKS ON LARGE LANGUAGE MODELS
    Dong, Yiting
    Shen, Guobin
    Zhao, Dongcheng
    He, Xiang
    Zeng, Yi
    arXiv,
12345