MLSP-P82: Adversarial Learning and Robustness in Deep Models I
Poster
Fri, 8 May, 14:00 - 16:00
Location: Poster Area 7
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P82.1: APMDET: DEFENDING AGAINST OBJECT-BASED ATTACKS FOR LIDAR DETECTION IN AUTONOMOUS DRIVING
Huiying Wang, Lisong Zhang, Yu Wen, Institute of Information Engineering, Chinese Academy of Sciences, China

MLSP-P82.2: CONSTRAINED LOCAL POINT CLOUD PERTURBATIONS USING ADAPTIVE CURVATURE FOR 3D ADVERSARIAL ATTACKS
Zhen Xu, Yuxi Luo, Kehao Cao, Xin Peng, Wei Zhang, Beijing University of Posts and Telecommunications, China; Ziyang Xiao, Luming Li, Hua Wang, Zhiping Wu, State Grid Jiangxi Electric Power Co., Ltd. Information and Communication Branch, China

MLSP-P82.3: BABI: BLACKLISTED ACCRETION FOR BACKDOOR INVERSION IN INSTRUCTION FINE-TUNED LLMS
Zhengxing Li, Pennsylvania State University, United States of America; Jayaram Raghuram, Anomalee Inc., United States of America; Guangmingmei Yang, David Miller, George Kesidis, Pennsylvania State University, United States of America

MLSP-P82.4: AUDIO CLASSIFICATION MODELS ARE VULNERABLE TO FILTER PERTURBATIONS
Justin Dettmer, Rheinisch-Westfälische Technische Hochschule Aachen University, Germany; Annelot Bosman, Leiden University, Netherlands; Igor Vatolkin, Holger H. Hoos, Rheinisch-Westfälische Technische Hochschule Aachen University, Germany

MLSP-P82.5: UNICAMO: A UNIVERSAL PHYSICAL CAMOUFLAGE FOR MULTISPECTRAL OBJECT DETECTOR
Jinyin Chen, Ye Han, Haibin Zheng, Zhejiang University of Technology, China; Xing Yang, National University of Defense Technology, China

MLSP-P82.6: UNIFIED NEURAL BACKDOOR REMOVAL WITH ONLY FEW CLEAN SAMPLES THROUGH UNLEARNING AND RELEARNING
Nay Myat Min, Hong Long Pham, Jun Sun, Singapore Management University, Singapore

MLSP-P82.7: DEFENSEMEL: ENHANCING ADVERSARIAL ROBUSTNESS OF MULTIMODAL ENTITY LINKING WITH MULTIMODAL LARGE LANGUAGE MODELS
Fang Wang, Peking University, China; Jiaxi Xu, University of International Relations, China; Mengyuan Tian, Renmin University of China, China; Minghao Hu, Zhunchen Luo, Xiaoying Bai, Advanced Institute of Big Data, Beijing, China

MLSP-P82.8: LORA-ENHANCED DYNAMICS: A STRONG BASELINE FOR TRANSFERABLE PERSON RE-IDENTIFICATION ADVERSARIAL ATTACK
Yi Huang, Chuanming Wang, Yue Xu, Xiaolong Zheng, Huadong Ma, Liang Liu, State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, China

MLSP-P82.9: Transferable Adversarial Attacks against Visual Language Models via Staged Semantic Reframing
Ang Li, Chunlin Qiu, Yunjie Ge, Lingchen Zhao, Qian Wang, Wuhan University, China

MLSP-P82.10: HIGH-FREQUENCY DETAIL COMPENSATION AND MULTI-SCALE FEATURE FUSION NET FOR UAV REMOTE SENSING OBJECT DETECTION
Kai Wang, Yunzuo Zhang, Haiming Jing, Qiankun Li, Luqi Zhang, Shijiazhuang Tiedao University, China