MLSP-P20.8
LANGUAGE GUIDED ADVERSARIAL PURIFICATION
Himanshu Singh, A V Subramanyam, Indraprastha Institute of Information Technology, India
Session:
MLSP-P20: Adversarial Machine Learning II Poster
Track:
Machine Learning for Signal Processing
Location:
Poster Zone 4C
Poster Board PZ-4C.8
Poster Board PZ-4C.8
Presentation Time:
Wed, 17 Apr, 16:30 - 18:30 (UTC +9)
Session Chair:
Konstantinos Drossos, Nokia Technologies
Session MLSP-P20
MLSP-P20.1: MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization
Zhaozhe Hu, Jia-Li Yin, Bin Chen, Luojun Lin, Fuzhou University, China; Bo-Hao Chen, Yuan Ze University, China; Ximeng Liu, Fuzhou University, China
MLSP-P20.2: ARCHITECTURE-AGNOSTIC ITERATIVE BLACK-BOX CERTIFIED DEFENSE AGAINST ADVERSARIAL PATCHES
Di Yang, East China Normal University, China; Yihao Huang, Nanyang Technological University, Singapore; Qing Guo, A*STAR, Singapore; Felix Juefei-Xu, New York University, United States of America; Ming Hu, Yang Liu, Nanyang Technological University, Singapore; Geguang Pu, East China Normal University, China
MLSP-P20.3: OADAS: OPTIMIZING GLOBAL PERTURBATION ATTACKS WITH DUAL-PATH ATTRIBUTION SYNERGY
Xinlei Gao, Jing Liu, Inner Mongolia University, China
MLSP-P20.4: TOWARDS VIDEO-TEXT RETRIEVAL ADVERSARIAL ATTACK
Haozhe Yang, Yuhan Xiang, Ke Sun, Jianlong Hu, Xianming Lin, Xiamen University, China
MLSP-P20.5: FIBA: FEDERATED INVISIBLE BACKDOOR ATTACK
Lu Zhang, Huazhong University of Science and Technology, China; Baolin Zheng, Alibaba Group, China
MLSP-P20.6: Identifying Attack-Specific Signatures in Adversarial Examples
Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Johns Hopkins University, United States of America; Micah Goldblum, New York University, United States of America; Rama Chellappa, Johns Hopkins University, United States of America
MLSP-P20.7: TEN-GUARD: TENSOR DECOMPOSITION FOR BACKDOOR ATTACK DETECTION IN DEEP NEURAL NETWORKS
Khondoker Hossain, Tim Oates, University of Maryland Baltimore County, United States of America
MLSP-P20.8: LANGUAGE GUIDED ADVERSARIAL PURIFICATION
Himanshu Singh, A V Subramanyam, Indraprastha Institute of Information Technology, India
MLSP-P20.9: Image Mixing and Gradient Smoothing to Enhance the SAR Image Attack Transferability
Yue Xu, Xin Liu, Kun He, Huazhong University of Science and Technology, China; Shao Huang, Yaodong Zhao, Jie Gu, National Key Laboratory of Electromagnetic Space Security, China
MLSP-P20.10: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models
Hongwei Yao, Zhejiang University, China; Jian Lou, ZJU-Hangzhou Global Scientific and Technological Innovation Center, China; Zhan Qin, Zhejiang University, China
MLSP-P20.11: Adversarial Representation Learning for Robust Privacy Preservation in Audio
Shayan Gharib, Minh Tran, Diep Luong, Konstantinos Drossos, Tuomas Virtanen, Tampere University - Faculty of Information Technology and Communication Sciences Korkeakoulunkatu 7 , Tampere FI-33720 Finland
Contacts