Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Fu, Feisi"'
Autor:
Fu, Feisi
Deep neural networks have demonstrated impressive performance in a wide variety of applications. However, deep neural networks are not perfect. In many cases, additional adjustments, which we call neural network editing, are essential for various obj
Externí odkaz:
https://hdl.handle.net/2144/48849
Autor:
Fu, Feisi, Li, Wenchao
Ownership verification for neural networks is important for protecting these models from illegal copying, free-riding, re-distribution and other intellectual property misuse. We present a novel methodology for neural network ownership verification ba
Externí odkaz:
http://arxiv.org/abs/2306.13215
We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant until it i
Externí odkaz:
http://arxiv.org/abs/2211.01808
With the increment of interest in leveraging machine learning technology in safety-critical systems, the robustness of neural networks under external disturbance receives more and more concerns. Global robustness is a robustness property defined on t
Externí odkaz:
http://arxiv.org/abs/2208.07289
Autor:
Fu, Feisi, Li, Wenchao
Publikováno v:
International Conference on Learning Representations, 2022
We present a novel methodology for repairing neural networks that use ReLU activation functions. Unlike existing methods that rely on modifying the weights of a neural network which can induce a global change in the function space, our approach appli
Externí odkaz:
http://arxiv.org/abs/2110.07682