6 papers
DIVE: Embedding Compression via Self-Limiting Gradient Updates
Dongfang Zhao
The paper introduces DIVE, a residual compression adapter that reduces the dimensionality of language‑model embeddings using a self‑limiting hinge loss, geometry distillation, and…
EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation
Dongfang Zhao
Vector search systems built on frozen vision encoders face queries from unseen classes at deployment, yet existing adapter training collapses under this shift: high-capacity adapte…
DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning
Jiayao Wang, Mohammad Maruf Hasan, Yiping Zhang +5
Self-Supervised Learning (SSL) has emerged as a significant paradigm in representation learning thanks to its ability to learn without extensive labeled data, its strong generaliza…
BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models
Jiayao Wang, Yiping Zhang, Mohammad Maruf Hasan +5
Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a distinct threat: unlike tradition…
ADCA: Attention-Driven Multi-Party Collusion Attack in Federated Self-Supervised Learning
Jiayao Wang, Yiping Zhang, Jiale Zhang +4
Federated Self-Supervised Learning (FSSL) integrates the privacy advantages of distributed training with the capability of self-supervised learning to leverage unlabeled data, show…
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…