Guy Amit (Ben-Gurion University), Moshe Levy (Ben-Gurion University), Yisroel Mirsky (Ben-Gurion University)

Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to hide rogue models within seemingly legitimate models. In addition, in this work we show that neural networks can be taught to systematically memorize and retrieve specific samples from datasets. Together, these findings expose a novel method in which adversaries can exfiltrate datasets from protected learning environments under the guise of legitimate models.

We focus on the data exfiltration attack and show that modern architectures can be used to secretly exfiltrate tens of thousands of samples with high fidelity, high enough to compromise data privacy and even train new models. Moreover, to mitigate this threat we propose a novel approach for detecting infected models.

View More Papers

Benchmarking transferable adversarial attacks

Zhibo Jin (The University of Sydney), Jiayu Zhang (Suzhou Yierqi), Zhiyu Zhu, Huaming Chen (The University of Sydney)

Read More

Heterogeneous Graph Pre-training Based Model for Secure and Efficient...

Xurui Li (Fudan University), Xin Shan (Bank of Shanghai), Wenhao Yin (Shanghai Saic Finance Co., Ltd)

Read More

File Hijacking Vulnerability: The Elephant in the Room

Chendong Yu (Institute of Information Engineering, Chinese Academy of Sciences and School of Cyber Security, University of Chinese Academy of Sciences), Yang Xiao (Institute of Information Engineering, Chinese Academy of Sciences and School of Cyber Security, University of Chinese Academy of Sciences), Jie Lu (Institute of Computing Technology of the Chinese Academy of Sciences), Yuekang…

Read More

EM Eye: Characterizing Electromagnetic Side-channel Eavesdropping on Embedded Cameras

Yan Long (University of Michigan), Qinhong Jiang (Zhejiang University), Chen Yan (Zhejiang University), Tobias Alam (University of Michigan), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejiang University), Kevin Fu (Northeastern University)

Read More