4 papers
GuidedRay: Diversity-Guided Direction Discovery for Targeted Hard-Label Black-Box Attacks
Fei Yuan, Yantian Shen, Qingyuan Yu +5
Deep neural networks are vulnerable to adversarial attacks. Among black-box attacks, targeted decision-based attacks are particularly difficult: the attacker observes only the targ…
Why Neural Structural Obfuscation Can't Kill White-Box Watermarks for Good!
Yanna Jiang, Guangsheng Yu, Qingyuan Yu +2
Neural Structural Obfuscation (NSO) (USENIX Security'23) is a family of ``zero cost'' structure-editing transforms (\texttt{nso\_zero}, \texttt{nso\_clique}, \texttt{nso\_split}) t…
Delving into Cryptanalytic Extraction of PReLU Neural Networks
Yi Chen, Xiaoyang Dong, Ruijie Ma +4
The machine learning problem of model extraction was first introduced in 1991 and gained prominence as a cryptanalytic challenge starting with Crypto 2020. For over three decades,…
Hard-Label Cryptanalytic Extraction of Neural Network Models
Yi Chen, Xiaoyang Dong, Jian Guo +3
The machine learning problem of extracting neural network parameters has been proposed for nearly three decades. Functionally equivalent extraction is a crucial goal for research o…