MLSP-L18.3
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
Fan Yang, Huazhong University of Science and Technology, China; Yihao Huang, National University of Singapore, Singapore; Ling Shi, Nanyang Technological University, Singapore; Geguang Pu, East China Normal University, China; Kailong Wang, Huazhong University of Science and Technology, China
Session:
MLSP-L18: Adversarial Learning and Robustness in Deep Models Oral
Track:
Machine Learning for Signal Processing [ML]
Location:
Room 112
Presentation Time:
Thu, 7 May, 09:40 - 10:00
Presentation
Discussion
Resources
No resources available.
Session MLSP-L18
MLSP-L18.1: AL-COLE: AUGMENTED LAGRANGIAN FOR CONSTRAINED LEARNING
Ignacio Boero, Ignacio Hounie, Alejandro Ribeiro, University of Pennsylvania, United States of America
MLSP-L18.2: OVERCOMING BINNING DILEMMA: CUMULATIVE CALIBRATION FOR DOUBLY ROBUST LEARNING IN DEBIASED RECOMMENDATION
Xiwen Jiang, Wenli Wang, Xiaofeng Meng, Renmin University of China, China; Tianyu Xia, Peking University, China
MLSP-L18.3: Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
Fan Yang, Huazhong University of Science and Technology, China; Yihao Huang, National University of Singapore, Singapore; Ling Shi, Nanyang Technological University, Singapore; Geguang Pu, East China Normal University, China; Kailong Wang, Huazhong University of Science and Technology, China
MLSP-L18.4: Defending 3D Point Clouds with Frequency-Guided Diffusion model
Qi Zhang, Haoqian Wang, Teng Li, National University of Defense Technology, China
MLSP-L18.5: WHEN VOICE MATTERS: A CONTROLLED STUDY OF AUDIO LLM BEHAVIOR IN CLINICAL DECISION-MAKING
Zhi Rui Tam, Yun-Nung Chen, National Taiwan University, Taiwan
MLSP-L18.6: HAD: HYBRID ADVERSARIAL DISTILLATION AGAINST ADVERSARIAL ATTACKS
Jing Zou, Shungeng Zhang, Meikang Qiu, Augusta University, United States of America
Contacts