5 papers · 1 filter
A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families
Yu Zhe, Yixin Tan, Junhao Wei +1
Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior work primarily attributes mergin…
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…
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…
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…
Adversarial Attacks on Hidden Tasks in Multi-Task Learning
Yu Zhe, Rei Nagaike, Daiki Nishiyama +2
Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective w…