Yichen Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yichen Ye has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Yiyuan Xie
Southwest University
12 shared publications - Xiao Jiang
College of Electronic and Information Engineering, Southwest University, Chongqing, China
5 shared publications - Ye Su
College of Electronic and Information Engineering, Southwest University, Chongqing, China
4 shared publications - Zhuang Chen
College of Electronic and Information Engineering, Southwest University, Chongqing, China
4 shared publications - Bocheng Liu
School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China
3 shared publications - Degang Yang
College of Computer and Information Science, Chongqing Normal University, Chongqing, China
3 shared publications
Latest Publications
- 3 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
LRCC: Robust point cloud understanding via low-rank refinement and curvature compensation
- 3 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
LRCC: Robust point cloud understanding via low-rank refinement and curvature compensation
- Top Cited Papers
- 5 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 176
RFAConv: Receptive-field attention convolution for improving convolutional neural networks
- 5 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 176
Top Cited PapersRFAConv: Receptive-field attention convolution for improving convolutional neural networks
- 21 January 2026
- Published by Elsevier in Digital Signal Processing
- Vol. 174
MA-YOLO: Enhanced multi-scale attentional remote sensing detector
- 21 January 2026
- Published by Elsevier in Digital Signal Processing
- Vol. 174
MA-YOLO: Enhanced multi-scale attentional remote sensing detector
- 14 January 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 336
Accelerating deep neural networks through stability-aware initial training and density-guided asymptotic filter decay
- 14 January 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 336
Accelerating deep neural networks through stability-aware initial training and density-guided asymptotic filter decay
- 8 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 43 (24) , 10795-10805
GGPD: Defending Against Phase Gradient Attack on Photonic Neural Networks
Integrated photonic neural networks (PNNs) offer a novel accelerated framework for information processing systems and are gradually influencing the future direction of Artificial Intelligence (AI). With silicon-based photonic platforms increasingly deployed in security-sensitive areas, the security of PNNs has become more critical. Attacks targeting the gradient ordering of photonic components and injecting disturbances along the gradient direction have significantly threatened the security of PNNs. However, defense mechanisms against such attacks remain underexplored. In this paper, a defense strategy for PNNs based on Mach-Zehnder interferometers (MZIs)—the gradient-guided phase defense (GGPD) technique—is proposed for the first time. By filtering the vulnerable phases along the learning direction, this method effectively mitigates the impact of attacks targeting high-risk photonic components. Additionally, a multi-stage defense (MSD) framework is introduced, which increases the number of target phases for GGPD. Experimental results demonstrate that, under attacks targeting 40 vulnerable phases, the proposed method achieves 92.21% and 74.70% accuracy on the MNIST and Fashion-MNIST datasets, respectively.
- 8 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 43 (24) , 10795-10805
GGPD: Defending Against Phase Gradient Attack on Photonic Neural Networks
Integrated photonic neural networks (PNNs) offer a novel accelerated framework for information processing systems and are gradually influencing the future direction of Artificial Intelligence (AI). With silicon-based photonic platforms increasingly deployed in security-sensitive areas, the security of PNNs has become more critical. Attacks targeting the gradient ordering of photonic components and injecting disturbances along the gradient direction have significantly threatened the security of PNNs. However, defense mechanisms against such attacks remain underexplored. In this paper, a defense strategy for PNNs based on Mach-Zehnder interferometers (MZIs)—the gradient-guided phase defense (GGPD) technique—is proposed for the first time. By filtering the vulnerable phases along the learning direction, this method effectively mitigates the impact of attacks targeting high-risk photonic components. Additionally, a multi-stage defense (MSD) framework is introduced, which increases the number of target phases for GGPD. Experimental results demonstrate that, under attacks targeting 40 vulnerable phases, the proposed method achieves 92.21% and 74.70% accuracy on the MNIST and Fashion-MNIST datasets, respectively.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (3) , 1290-1303
A Novel MDM-Based Optical Networks-on-Chip With Reliability Analysis
Ever-increasing demands for lower power loss, shorter transmission delay, and higher communication capacity have been a challenge in optical networks-on-chips (ONoCs). To address this, various multiplexing technologies have been proposed and applied to optical interconnection networks. Among these, mode-division multiplexing (MDM) technology stands out for its ability to significantly enhance network throughput and reduce communication delays by simultaneously transmitting multiple-mode optical signals through a multimode waveguide, making it a compelling research area. In this article, we propose a flexible and scalable multimode optical switching element (MOSE) that adjusts transmitted optical signals by modifying its structure. A multimode optical router (MOR) based on the proposed MOSE is introduced, followed by the design of MDM-based optical mesh networks-on-chip (MMONoCs) that support parallel transmission of multiple TE-polarization mode optical signals. Additionally, loss and crosstalk models for multimode optical devices, including MOSE and MOR, are systematically established. In conclusion, the loss, optical signal-to-noise ratio (OSNR), and bit error rate (BER) for three TE-polarization modes (TE0, TE1, and TE2) at different network scales are analyzed using MOR as a specific example. The findings indicate that the scalability of MMONoC and its communication quality are mainly influenced by mode crosstalk noise. Furthermore, network performance metrics, including end-to-end (ETE) delay and throughput, are discussed based on two-mode (TE0, TE1) and three-mode (TE0, TE1, and TE2) optical signals at 1550 nm in $4\times 4$ and $5\times 5$ optical mesh networks. Simulation results demonstrate that MMONoC exhibits significant improvements in ETE delay and throughput compared to traditional single-mode optical modes.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (3) , 1290-1303
A Novel MDM-Based Optical Networks-on-Chip With Reliability Analysis
Ever-increasing demands for lower power loss, shorter transmission delay, and higher communication capacity have been a challenge in optical networks-on-chips (ONoCs). To address this, various multiplexing technologies have been proposed and applied to optical interconnection networks. Among these, mode-division multiplexing (MDM) technology stands out for its ability to significantly enhance network throughput and reduce communication delays by simultaneously transmitting multiple-mode optical signals through a multimode waveguide, making it a compelling research area. In this article, we propose a flexible and scalable multimode optical switching element (MOSE) that adjusts transmitted optical signals by modifying its structure. A multimode optical router (MOR) based on the proposed MOSE is introduced, followed by the design of MDM-based optical mesh networks-on-chip (MMONoCs) that support parallel transmission of multiple TE-polarization mode optical signals. Additionally, loss and crosstalk models for multimode optical devices, including MOSE and MOR, are systematically established. In conclusion, the loss, optical signal-to-noise ratio (OSNR), and bit error rate (BER) for three TE-polarization modes (TE0, TE1, and TE2) at different network scales are analyzed using MOR as a specific example. The findings indicate that the scalability of MMONoC and its communication quality are mainly influenced by mode crosstalk noise. Furthermore, network performance metrics, including end-to-end (ETE) delay and throughput, are discussed based on two-mode (TE0, TE1) and three-mode (TE0, TE1, and TE2) optical signals at 1550 nm in $4\times 4$ and $5\times 5$ optical mesh networks. Simulation results demonstrate that MMONoC exhibits significant improvements in ETE delay and throughput compared to traditional single-mode optical modes.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 31 (3: AI/ML I) , 1-11
A Formal Scheme of Fault Injection on Coherent Integrated Photonic Neural Networks
Based on Mach-Zehnder interferometers (MZIs) coherent integrated photonic neural networks (PNNs) may provide a promising solution for the realization of deep learning with low power consumption, low latency, and ultra-high speed. Adversarial attacks have been widely confirmed to be a serious threat to deep learning. This has led to a large amount of studies in this direction of the electronic domain, including input attacks and inject faults for weights. In this paper, focusing on the phases in the linear operation unit of PNNs, a phase gradient attack (PGA) scheme based on the phase gradient sorting of the MZI-arrays and injecting disturbances along the gradient direction is proposed for the first time. The simulation results indicate that even with weak-intensity PGA, it is almost impossible for PNNs to perform the classification inference. Furthermore, taking into account the effects of fabrication-process variations (FPV) and thermal crosstalk in MZI-arrays that lead to tuning phase deviation in practical application, we systematically analyzed the validity of proposed scheme on the PNNs with phase uncertainties. Specifically, we tested the impact of injecting faults by compressing the number of attacked phase angles to 3, 5, and 7, respectively. The experiment results show that injection attack based using PGA on PNNs trained with Gaussian datasets would reduce classification accuracy to 27.97%, 15.47%, and 8.91% for corresponding cases.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 31 (3: AI/ML I) , 1-11
A Formal Scheme of Fault Injection on Coherent Integrated Photonic Neural Networks
Based on Mach-Zehnder interferometers (MZIs) coherent integrated photonic neural networks (PNNs) may provide a promising solution for the realization of deep learning with low power consumption, low latency, and ultra-high speed. Adversarial attacks have been widely confirmed to be a serious threat to deep learning. This has led to a large amount of studies in this direction of the electronic domain, including input attacks and inject faults for weights. In this paper, focusing on the phases in the linear operation unit of PNNs, a phase gradient attack (PGA) scheme based on the phase gradient sorting of the MZI-arrays and injecting disturbances along the gradient direction is proposed for the first time. The simulation results indicate that even with weak-intensity PGA, it is almost impossible for PNNs to perform the classification inference. Furthermore, taking into account the effects of fabrication-process variations (FPV) and thermal crosstalk in MZI-arrays that lead to tuning phase deviation in practical application, we systematically analyzed the validity of proposed scheme on the PNNs with phase uncertainties. Specifically, we tested the impact of injecting faults by compressing the number of attacked phase angles to 3, 5, and 7, respectively. The experiment results show that injection attack based using PGA on PNNs trained with Gaussian datasets would reduce classification accuracy to 27.97%, 15.47%, and 8.91% for corresponding cases.
- 29 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
Reservoir computing based encryption-then-compression scheme of image achieving lossless compression
- 29 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
Reservoir computing based encryption-then-compression scheme of image achieving lossless compression
- 29 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nanotechnology
- Vol. 22 (1536125X) , 349-358
A Novel Approach for Achieving Slow Light With Ultra-Low Dispersion in Plasmonic Device
Compact slow light devices are essential components for performing data caching and signal processing in photonic integrated loops. In this paper, an integrated ultra-low-dispersion slow light device with a novel method is proposed. The device consists of three parts (hexagonal resonator with elliptical core, stub cavity, and tooth cavities) coupled to the waveguide, respectively. Dual Fano resonances occur in the structure, and transmission characteristics of the structure are investigated in detail by temporal coupled-mode theory. Finite-difference time-domain simulations reveal that the transmission bandwidth, group index, and delay time can be manipulated by adjusting the separation between two Fano resonances, which is related to the eccentricity of the oval core. At the 850.7 nm window, transmission bandwidth and average group index are optimized to 21.1 nm and 12.19, respectively. Moreover, multiple dispersionless wavelengths within the slow light bandwidth are obtained based on dual Fano resonances. Furthermore, feasibility of the device to perform slow light function in different channels is researched, and device performance is presented and analyzed. This device has a great impact on improving the quality of signals on chips, and the method introduced is of great significance for designing other photonic devices.
- 29 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nanotechnology
- Vol. 22 (1536125X) , 349-358
A Novel Approach for Achieving Slow Light With Ultra-Low Dispersion in Plasmonic Device
Compact slow light devices are essential components for performing data caching and signal processing in photonic integrated loops. In this paper, an integrated ultra-low-dispersion slow light device with a novel method is proposed. The device consists of three parts (hexagonal resonator with elliptical core, stub cavity, and tooth cavities) coupled to the waveguide, respectively. Dual Fano resonances occur in the structure, and transmission characteristics of the structure are investigated in detail by temporal coupled-mode theory. Finite-difference time-domain simulations reveal that the transmission bandwidth, group index, and delay time can be manipulated by adjusting the separation between two Fano resonances, which is related to the eccentricity of the oval core. At the 850.7 nm window, transmission bandwidth and average group index are optimized to 21.1 nm and 12.19, respectively. Moreover, multiple dispersionless wavelengths within the slow light bandwidth are obtained based on dual Fano resonances. Furthermore, feasibility of the device to perform slow light function in different channels is researched, and device performance is presented and analyzed. This device has a great impact on improving the quality of signals on chips, and the method introduced is of great significance for designing other photonic devices.
- Open Access
Design of All-Optical Subtractors Utilized with Plasmonic Ring Resonators for Optical Computing
In this paper, a novel plasmonic all-optical half-subtractor and full-subtractor are designed for optical computing. The structure of plasmonic subtractors consists of a metal–insulator–metal (MIM) waveguide and rectangular ring resonators covered by a graphene layer. Due to the nonlinear optical properties of graphene, the states of the plasmonic resonators can be controlled by the pump intensity of a pump beam focused on the graphene layer. The resonators can work as all-optical switches with an ultra-fast response time to constitute optical logic devices according to the directed logic mechanism. A finite-difference time-domain method is utilized to numerically investigate the transmission of the output signals which represent the results of subtraction operations. Simulation results obtained indicate that the proposed plasmonic devices have the ability to implement half-subtraction and full-subtraction with a small feature size and fast response time, and provide a new concept and method for the design and realization of optical computing devices.
Open AccessDesign of All-Optical Subtractors Utilized with Plasmonic Ring Resonators for Optical Computing
In this paper, a novel plasmonic all-optical half-subtractor and full-subtractor are designed for optical computing. The structure of plasmonic subtractors consists of a metal–insulator–metal (MIM) waveguide and rectangular ring resonators covered by a graphene layer. Due to the nonlinear optical properties of graphene, the states of the plasmonic resonators can be controlled by the pump intensity of a pump beam focused on the graphene layer. The resonators can work as all-optical switches with an ultra-fast response time to constitute optical logic devices according to the directed logic mechanism. A finite-difference time-domain method is utilized to numerically investigate the transmission of the output signals which represent the results of subtraction operations. Simulation results obtained indicate that the proposed plasmonic devices have the ability to implement half-subtraction and full-subtraction with a small feature size and fast response time, and provide a new concept and method for the design and realization of optical computing devices.