Tian Dong (Shanghai Jiao Tong University), Shaofeng Li (Shanghai Jiao Tong University), Guoxing Chen (Shanghai Jiao Tong University), Minhui Xue (CSIRO's Data61), Haojin Zhu (Shanghai Jiao Tong University), Zhen Liu (Shanghai Jiao Tong University)

Identity plays an important role in responsible artificial intelligence (AI): it acts as a unique marker for deep learning (DL) models and can be used to trace those accountable for irresponsible use of models. Consequently, effective DL identity audit is fundamental for building responsible AI. Besides models, training datasets determine what features a model can learn, and thus should be paid equal attention in identity audit. In this work, we propose the first practical scheme, named RAI2, for responsible identity audit for both datasets and models. We develop our dataset and model similarity estimation methods that can work with black-box access to suspect models. The proposed methods can quantitatively determine the identity of datasets and models by estimating the similarity between the owner's and suspect's. Finally, we realize our responsible audit scheme based on the commitment scheme, enabling the owner to register datasets and models to a trusted third party (TTP) which is in charge of dataset and model regulation and forensics of copyright infringement. Extensive evaluation on 14 model architectures and 6 visual and textual datasets shows that our scheme can accurately identify the dataset and model with the proposed similarity estimation methods. We hope that our audit methodology will not only fill the gap in achieving identity arbitration but also ride on the wave of AI governance in this chaotic world.

View More Papers

Analysing Adversarial Threats to Rule-Based Local-Planning Algorithms for Autonomous...

Andrew Roberts (Tallinn University of Technology), Mohsen Malayjerdi (Tallinn University of Technology), Mauro Bellone (Tallinn University of Technology), Olaf Maennel (The University of Adelaide), Ehsan Malayjerdi (Tallinn University of Technology)

Read More

Preventing SIM Box Fraud Using Device Model Fingerprinting

BeomSeok Oh (KAIST), Junho Ahn (KAIST), Sangwook Bae (KAIST), Mincheol Son (KAIST), Yonghwa Lee (KAIST), Min Suk Kang (KAIST), Yongdae Kim (KAIST)

Read More

Copy-on-Flip: Hardening ECC Memory Against Rowhammer Attacks

Andrea Di Dio (Vrije Universiteit Amsterdam), Koen Koning (Intel), Herbert Bos (Vrije Universiteit Amsterdam), Cristiano Giuffrida (Vrije Universiteit Amsterdam)

Read More

Do Not Give a Dog Bread Every Time He...

Chongqing Lei (Southeast University), Zhen Ling (Southeast University), Yue Zhang (Jinan University), Kai Dong (Southeast University), Kaizheng Liu (Southeast University), Junzhou Luo (Southeast University), Xinwen Fu (University of Massachusetts Lowell)

Read More