يعرض 1 - 13 نتائج من 13 نتيجة بحث عن '"Hong, Hanbin"', وقت الاستعلام: 0.52s تنقيح النتائج
  1. 1
    Report
    GALOT: Generative Active Learning via Optimizable Zero-shot Text-to-image Generation

    المؤلفون: Hong, Hanbin, Yan, Shenao, Feng, Shuya, Yan, Yan, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning

    URL الوصول: http://arxiv.org/abs/2412.16227

    View record in Arxiv

    أضف إلى المفضلة
  2. 2
    Report
    Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence

    المؤلفون: Feng, Shuya, Mohammady, Meisam, Hong, Hanbin, Yan, Shenao, Kundu, Ashish, Wang, Binghui, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Cryptography and Security

    URL الوصول: http://arxiv.org/abs/2407.14710

    View record in Arxiv

    أضف إلى المفضلة
  3. 3
    Report
    An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

    المؤلفون: Yan, Shenao, Wang, Shen, Duan, Yue, Hong, Hanbin, Lee, Kiho, Kim, Doowon, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence, Computer Science - Software Engineering

    URL الوصول: http://arxiv.org/abs/2406.06822

    View record in Arxiv

    أضف إلى المفضلة
  4. 4
    Report
    Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness

    المؤلفون: Deng, Jieren, Hong, Hanbin, Palmer, Aaron, Zhou, Xin, Bi, Jinbo, Mahmood, Kaleel, Hong, Yuan, Aguiar, Derek

    مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Cryptography and Security, Computer Science - Computer Vision and Pattern Recognition

    URL الوصول: http://arxiv.org/abs/2405.16036

    View record in Arxiv

    أضف إلى المفضلة
  5. 5
    Report
    Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

    المؤلفون: Zhang, Xinyu, Hong, Hanbin, Hong, Yuan, Huang, Peng, Wang, Binghui, Ba, Zhongjie, Ren, Kui

    مصطلحات موضوعية: Computer Science - Cryptography and Security, Computer Science - Computation and Language, Computer Science - Machine Learning

    URL الوصول: http://arxiv.org/abs/2307.16630

    View record in Arxiv

    أضف إلى المفضلة
  6. 6
    Report
    Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence

    المؤلفون: Hong, Hanbin, Zhang, Xinyu, Wang, Binghui, Ba, Zhongjie, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Cryptography and Security

    URL الوصول: http://arxiv.org/abs/2304.04343

    View record in Arxiv

    أضف إلى المفضلة
  7. 7
    Report
    L-SRR: Local Differential Privacy for Location-Based Services with Staircase Randomized Response

    المؤلفون: Wang, Han, Hong, Hanbin, Xiong, Li, Qin, Zhan, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Cryptography and Security

    URL الوصول: http://arxiv.org/abs/2209.15091

    View record in Arxiv

    أضف إلى المفضلة
  8. 8
    Report
    Certified Adversarial Robustness via Anisotropic Randomized Smoothing

    المؤلفون: Hong, Hanbin, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

    URL الوصول: http://arxiv.org/abs/2207.05327

    View record in Arxiv

    أضف إلى المفضلة
  9. 9
    Report
    UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

    المؤلفون: Hong, Hanbin, Wang, Binghui, Hong, Yuan

    مصطلحات موضوعية: Computer Science - Machine Learning

    URL الوصول: http://arxiv.org/abs/2207.02152

    View record in Arxiv

    أضف إلى المفضلة
  10. 10
    Report
    An Eye for an Eye: Defending against Gradient-based Attacks with Gradients

    المؤلفون: Hong, Hanbin, Hong, Yuan, Kong, Yu

    مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Cryptography and Security, Computer Science - Machine Learning

    URL الوصول: http://arxiv.org/abs/2202.01117

    View record in Arxiv

    أضف إلى المفضلة
  11. 11
    Academic Journal
    An LLM-assisted easy-to-trigger poisoning attack on code completion models: Injecting disguised vulnerabilities against strong detection

    المؤلفون: YAN, Shenao, WANG, Shen, DUAN, Yue, HONG, Hanbin, LEE, Kiho, KIM, Doowon, HONG, Yuan

    المصدر: Research Collection School Of Computing and Information Systems

    مصطلحات موضوعية: Information Security

    وصف الملف: application/pdf

    Relation: https://ink.library.smu.edu.sg/sis_research/8962; https://ink.library.smu.edu.sg/context/sis_research/article/9965/viewcontent/2406.06822v1.pdf

    الاتاحة: https://ink.library.smu.edu.sg/sis_research/8962
    https://ink.library.smu.edu.sg/context/sis_research/article/9965/viewcontent/2406.06822v1.pdf

    View record in BASE

    أضف إلى المفضلة
  12. 12
    Conference
    Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

    المؤلفون: Zhang, Xinyu, Hong, Hanbin, Hong, Yuan, Huang, Peng, Wang, Binghui, Ba, Zhongjie, Ren, Kui

    المساهمون: National Natural Science Foundation of China, National Science Foundation

    المصدر: 2024 IEEE Symposium on Security and Privacy (SP) ; page 2920-2938

    الاتاحة: http://dx.doi.org/10.1109/sp54263.2024.00053
    http://xplorestaging.ieee.org/ielx8/10646615/10646598/10646716.pdf?arnumber=10646716

    View record in BASE

    أضف إلى المفضلة
  13. 13
    Electronic Resource
    Certifiable Black-Box Attack: Ensuring Provably Successful Attack for Adversarial Examples

    المؤلفون: Hong, Hanbin, Hong, Yuan

    مصطلحات الفهرس: Computer Science - Machine Learning, Computer Science - Cryptography and Security, text

    URL: http://arxiv.org/abs/2304.04343

    View record in OAIster

    أضف إلى المفضلة
أدوات البحث: أحصل على تغذية RSS – أرسل هذا البحث بالبريد الإلكتروني – حفظ البحث – جدول التنبيهات: لا شيء