6 papers
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
Chi Wang, Hanwen Wang, Yu Xia +2
We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision…
Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
Zihan Wang, Zhiyong Ma, Zhongkui Ma +5
Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose…
Re-Key-Free, Risky-Free: Adaptable Model Usage Control
Zihan Wang, Zhongkui Ma, Xinguo Feng +6
Deep neural networks (DNNs) have become valuable intellectual property of model owners, due to the substantial resources required for their development. To protect these assets in…
AI Model Modulation with Logits Redistribution
Zihan Wang, Zhongkui Ma, Xinguo Feng +5
Large-scale models are typically adapted to meet the diverse requirements of model owners and users. However, maintaining multiple specialized versions of the model is inefficient.…
Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation
Xinguo Feng, Zhongkui Ma, Zihan Wang +2
Training and fine-tuning large-scale language models largely benefit from collaborative learning, but the approach has been proven vulnerable to gradient inversion attacks (GIAs),…
Uncovering Gradient Inversion Risks in Practical Language Model Training
Xinguo Feng, Zhongkui Ma, Zihan Wang +4
The gradient inversion attack has been demonstrated as a significant privacy threat to federated learning (FL), particularly in continuous domains such as vision models. In contras…