activity
20242026
collaborators

7 papers

cs.CV2026

Filtering Memorization from Parameter-Space in Diffusion Models

Yu Zhe, Yang Jiayan, Wei Junhao +2

Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter…

cs.CL2026

When Benchmarks Leak: Inference-Time Decontamination for LLMs

Jianzhe Chai, Yu Zhe, Jun Sakuma

Benchmark-based evaluation is the de facto standard for comparing large language models (LLMs). However, its reliability is increasingly threatened by test set contamination, where…

cs.LG2025

Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy

Wei Junhao, Yu Zhe, Sakuma Jun

Model merging is a technique that combines multiple finetuned models into a single model without additional training, allowing a free-rider to cheaply inherit specialized capabilit…

cs.LG2025

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors

Chia-Yi Hsu, Yu-Lin Tsai, Yu Zhe +6

Task arithmetic in large-scale pre-trained models enables agile adaptation to diverse downstream tasks without extensive retraining. By leveraging task vectors (TVs), users can per…

cs.LG2025

Beyond Full Poisoning: Effective Availability Attacks with Partial Perturbation

Yu Zhe, Jun Sakuma

The widespread use of publicly available datasets for training machine learning models raises significant concerns about data misuse. Availability attacks have emerged as a means f…

cs.CV2024

Zero-shot domain adaptation based on dual-level mix and contrast

Yu Zhe, Jun Sakuma

Zero-shot domain adaptation (ZSDA) is a domain adaptation problem in the situation that labeled samples for a target task (task of interest) are only available from the source doma…