Author name cluster

Chengzhi Jiang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization

Runhao Jiang
Chengzhi Jiang
Rui Yan
Huajin Tang

The surrogate gradient (SG) method has shown significant promise in enhancing the performance of deep spiking neural networks (SNNs), but it also introduces vulnerabilities to adversarial attacks. Although spike coding strategies and neural dynamics parameters have been extensively studied for their impact on robustness, the critical role of gradient magnitude, which reflects the model's sensitivity to input perturbations, remains underexplored. In SNNs, the gradient magnitude is primarily determined by the interaction between the membrane potential distribution (MPD) and the SG function. In this study, we investigate the relationship between the MPD and SG and their implications for improving the robustness of SNNs. Our theoretical analysis reveals that reducing the proportion of membrane potentials lying within the gradient-available range of the SG function effectively mitigates the sensitivity of SNNs to input perturbations. Building upon this insight, we propose a novel MPD-driven surrogate gradient regularization (MPD-SGR) method, which enhances robustness by explicitly regularizing the MPD based on its interaction with the SG function. Extensive experiments across multiple image classification benchmarks and diverse network architectures confirm that the MPD-SGR method significantly enhances the resilience of SNNs to adversarial perturbations and exhibits strong generalizability across diverse network configurations, SG functions, and spike encoding schemes.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Diff-Shadow: Global-guided Diffusion Model for Shadow Removal

Jinting Luo
Ru Li
Chengzhi Jiang
Xiaoming Zhang
Mingyan Han
Ting Jiang
Haoqiang Fan
Shuaicheng Liu

We propose Diff-Shadow, a global-guided diffusion model for high-quality shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but they are not exempt from issues related to inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to realize shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextual information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on three publicly standard datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the ISTD dataset.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Realistic Noise Synthesis with Diffusion Models

Qi Wu
Mingyan Han
Ting Jiang
Chengzhi Jiang
Jinting Luo
Man Jiang
Haoqiang Fan
Shuaicheng Liu

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis Diffusor (RNSD) method using diffusion models to address these challenges. By encoding camera settings into a time-aware camera-conditioned affine modulation (TCCAM), RNSD generates more realistic noise distributions under various camera conditions. Additionally, RNSD integrates a multi-scale content-aware module (MCAM), enabling the generation of structured noise with spatial correlations across multiple frequencies. We also introduce Deep Image Prior Sampling (DIPS), a learnable sampling sequence based on depth image prior, which significantly accelerates the sampling process while maintaining the high quality of synthesized noise. Extensive experiments demonstrate that our RNSD method significantly outperforms existing techniques in synthesizing realistic noise under multiple metrics and improving image denoising performance.

PDF Details DOI

EAAI Journal 2024 Journal Article

Secured mutual wireless communication using real and imaginary-valued artificial neuronal synchronization and attack detection

Chengzhi Jiang
Arindam Sarkar
Abdulfattah Noorwali
Rahul Karmakar
Kamal M. Othman
Sarbajit Manna

This research presents a cutting-edge security framework that integrates optimal Intrusion Detection System (IDS) and Artificial Neural Networks (ANNs)-based key exchange methods to enhance the reliability of mutual wireless communication in Internet of Medical Things (IoMT) networks. The advent of IoMT technology has brought about a significant transformation in patient care and healthcare operations. It allows for real-time monitoring and diagnosis to be conducted remotely. However, the protection of sensitive medical data has become a crucial issue that has to be addressed to maintain privacy and security. IoMT devices, which have limited processing capabilities, are especially susceptible to cyberattacks, therefore requiring the implementation of new security measures. The proposed methodology offers numerous advantages. By utilizing patient sensor data and analyzing network traffic, the suggested solution surpasses current methods in identifying and preventing network threats with increased precision. This research showcases the better effectiveness of Deep Learning (DL) models in identifying intrusions in IoMT settings, by examining 17 Machine Learning (ML) and 6 DL models. The suggested methodology relies on using a neural sequence of ANNs that consist of both real and imaginary-valued components. This approach enables reciprocal learning and synchronization, which in turn facilitates safe key distribution among IoMT devices. This novel method not only guarantees strong key exchange mechanisms but also enhances the overall security of IoMT networks. This paper presents a complete solution to solve the difficulties of protecting wireless communication in IoMT contexts. This approach performs better than comparable methods in the literature.

Details DOI