Shiming Wang (Shanghai Jiao Tong University), Zhe Ji (Shanghai Jiao Tong University), Liyao Xiang (Shanghai Jiao Tong University), Hao Zhang (Shanghai Jiao Tong University), Xinbing Wang (Shanghai Jiao Tong University), Chenghu Zhou (Chinese Academy of Sciences), Bo Li (Hong Kong University of Science and Technology)

With the increased capabilities at the edge (e.g., mobile device) and more stringent privacy requirement, it becomes a recent trend for deep learning-enabled applications to pre-process sensitive raw data at the edge and transmit the features to the backend cloud for further processing. A typical application is to run machine learning (ML) services on facial images collected from different individuals. To prevent identity theft, conventional methods commonly rely on an adversarial game-based approach to shed the identity information from the feature. However, such methods can not defend against adaptive attacks, in which an attacker takes a countermove against a known defence strategy.

We propose Crafter, a feature crafting mechanism deployed at the edge, to protect the identity information from adaptive model inversion attacks while ensuring the ML tasks are properly carried out in the cloud. The key defence strategy is to mislead the attacker to a non-private prior from which the attacker gains little about the private identity. In this case, the crafted features act like poison training samples for attackers with adaptive model updates. Experimental results indicate that Crafter successfully defends both basic and possible adaptive attacks, which can not be achieved by state-of-the-art adversarial game-based methods.

View More Papers

Securing Automotive Software Supply Chains (Long)

Marina Moore, Aditya Sirish A Yelgundhalli (New York University), Justin Cappos (NYU)

Read More

LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions,...

Takami Sato (University of California, Irvine), Yuki Hayakawa (Keio University), Ryo Suzuki (Keio University), Yohsuke Shiiki (Keio University), Kentaro Yoshioka (Keio University), Qi Alfred Chen (University of California, Irvine)

Read More

Stacking up the LLM Risks: Applied Machine Learning Security

Dr. Gary McGraw, Berryville Institute of Machine Learning

Read More

WIP: Shadow Hack: Adversarial Shadow Attack Against LiDAR Object...

Ryunosuke Kobayashi, Kazuki Nomoto, Yuna Tanaka, Go Tsuruoka (Waseda University), Tatsuya Mori (Waseda University/NICT/RIKEN)

Read More