3 papers
cs.CR2026
Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
Zeyao Liu, Zhendong Zhao, Xiaojun Chen +3
Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the V…
cs.CR2026
HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
Jiayao Wang, Yang Song, Zhendong Zhao +5
Federated self-supervised learning (FSSL) enables collaborative training of self-supervised representation models without sharing raw unlabeled data. While it serves as a crucial p…
cs.CR2025
IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
Jiayao Wang, Yang Song, Zhendong Zhao +4
Federated self-supervised learning (FSSL) combines the advantages of decentralized modeling and unlabeled representation learning, serving as a cutting-edge paradigm with strong po…