IFS-P7.1
ENHANCING TARGETED TRANSFERABILITY VIA FEATURE SPACE FINE-TUNING
Hui Zeng, Southwest university of science and technology, China; Biwei Chen, Beijing Normal University, China; Anjie Peng, Southwest university of science and technology, China
Session:
IFS-P7: Adversarial Machine Learning Poster
Track:
Information Forensics and Security
Location:
Poster Zone 5A
Poster Board PZ-5A.1
Poster Board PZ-5A.1
Presentation Time:
Thu, 18 Apr, 16:30 - 18:30 (UTC +9)
Session IFS-P7
IFS-P7.1: ENHANCING TARGETED TRANSFERABILITY VIA FEATURE SPACE FINE-TUNING
Hui Zeng, Southwest university of science and technology, China; Biwei Chen, Beijing Normal University, China; Anjie Peng, Southwest university of science and technology, China
IFS-P7.2: DELVING DEEPER INTO VULNERABLE SAMPLES IN ADVERSARIAL TRAINING
Pengfei Zhao, Haojie Yuan, Qi Chu, Shubin Xu, Nenghai Yu, University of Science and Technology of China, China
IFS-P7.3: SYNTHESIZING BLACK-BOX ANTI-FORENSICS DEEPFAKES WITH HIGH VISUAL QUALITY
Bing Fan, Nanchang University, China; Shu Hu, Purdue University in Indianapolis, United States of America; FENG DING, Nanchang University, China
IFS-P7.4: Attribution-based Scanline Perturbation Attack on 3D Detectors of LiDAR Point Clouds
Ziyang Yu, Ting Yang, Dalian University of Technology, China; Qiong Chang, Tokyo Institute of Technology, Japan; Yu Liu, Weimin Wang, Dalian University of Technology, Japan
IFS-P7.5: CNFA: Conditional Normalizing Flow for Query-Limited Attack
Renyang Liu, Wei Zhou, Jinhong Zhang, Yunnan University, China; Haoran Li, Northeastern University, China; Ruxin Wang, Alibaba Group, China
IFS-P7.6: Enhancing Adversarial Robustness of DNNs via Weight Decorrelation in Training
Cong Zhang, China, China; Yuezun Li, Ocean University of China, China; Honggang Qi, University of Chinese Academy of Sciences, China; Siwei Lyu, University at Buffalo, United States of America
IFS-P7.7: Scalable Ensemble-based Detection Method Against Adversarial Attacks For Speaker Verification
Haibin Wu, Heng-Cheng Kuo, National Taiwan University, China; Yu Tsao, Research Center for Information Technology Innovation, Academia Sinica, Taiwan, Taiwan; Hung-yi Lee, National Taiwan University, Taiwan
IFS-P7.8: POISONING-FREE DEFENSE AGAINST BLACK-BOX MODEL EXTRACTION
Haitian Zhang, Wuhan University, China; Guang Hua, Singapore Institute of Technology, Singapore; Wen Yang, Wuhan University, China
IFS-P7.9: UNIVERSAL ADVERSARIAL ATTACK AGAINST SPEAKER RECOGNITION MODELS
Shoham Hanina, Alon Zolfi, Yuval Elovici, Asaf Shabtai, Ben Gurion University of the Negev, Israel
IFS-P7.10: DOMAIN ADAPTIVE GRAPH CLASSIFICATION
Siyang Luo, Shanghai Infortech Software Development Co., Ltd, China; Ziyi Jiang, New York University Shanghai, China; Zhenghan Chen, Peking University, China; Xiaoxuan Liang, University of Massachusetts Amherst, China
Contacts