Xiangyuan Yang

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 9

Top Topics

Top Venues

Publications

Xiangyuan Yang, Jie Lin, Hanlin Zhang, Peng Zhao
Improving query efficiency of black-box attacks via the preference of deep learning models. Inf. Sci. 678 (2024)
Zhaoxi Mu, Xinyu Yang, Xiangyuan Yang, Wenjing Zhu
A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments. CoRR (2023)
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Improving the Transferability of Adversarial Examples via Direction Tuning. CoRR (2023)
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Fuzziness-tuned: Improving the Transferability of Adversarial Examples. CoRR (2023)
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Improving the transferability of adversarial examples via direction tuning. Inf. Sci. 647 (2023)
Zhaoxi Mu, Xinyu Yang, Xiangyuan Yang, Wenjing Zhu
A Multi-Stage Triple-Path Method For Speech Separation in Noisy and Reverberant Environments. ICASSP (2023)
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Mask-Guided Divergence Loss Improves the Generalization and Robustness of Deep Neural Network. CoRR (2022)
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Enhancing the Transferability of Adversarial Examples via a Few Queries. CoRR (2022)
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
FACM: Correct the Output of Deep Neural Network with Middle Layers Features against Adversarial Samples. CoRR (2022)