4 papers
Evading Data Provenance in Deep Neural Networks
Hongyu Zhu, Sichu Liang, Wenwen Wang +3
Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. Howeve…
Revisiting Data Auditing in Large Vision-Language Models
Hongyu Zhu, Sichu Liang, Wenwen Wang +5
With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great poten…
Efficient and Effective Model Extraction
Hongyu Zhu, Wentao Hu, Sichu Liang +3
Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor t…
Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
Hongyu Zhu, Sichu Liang, Wentao Hu +3
With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective meas…