Query：
学者姓名：柳晓龙
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
In recent years, deep neural networks (DNNs) have made significant advancements in various vision tasks, including image classification and object detection. However, these models remain vulnerable to adversarial examples subtle perturbations that can significantly mislead predictions. In response to this, we propose a novel adversarial attack method called Local Masking and Multi-stage Momentum Optimization (LMMMO). LMMMO integrates a self-adaptive local masking mechanism to focus perturbations on decision-critical regions, improving both attack efficiency and perceptual stealth. Additionally, LMMMO uses a multi-stage momentum optimization strategy, adjusting step sizes dynamically and refining gradients through a coarse-to-fine approach to ensure stable convergence. Compared to existing methods, LMMMO achieves competitive high attack success rates (e.g., 0.989 average ASR) while demonstrating the lowest average L2 distortion (0.234). It also shows favorable perceptual similarity (LPIPS) compared to several iterative baselines like PGD and MIFGSM, offering a promising balance between attack performance and imperceptibility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
Keyword ：
Deep neural networks Deep neural networks Image classification Image classification Iterative methods Iterative methods Momentum Momentum Object detection Object detection Object recognition Object recognition
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Liqiang , Lin, Yu , Kang, Yunyu et al. An Adversarial Attack Method Based on Local Masking and Multi-stage Momentum Optimization [C] . 2026 : 329-341 . |
| MLA | Lin, Liqiang et al. "An Adversarial Attack Method Based on Local Masking and Multi-stage Momentum Optimization" . (2026) : 329-341 . |
| APA | Lin, Liqiang , Lin, Yu , Kang, Yunyu , Chen, Shuwu , Liu, Xiaolong . An Adversarial Attack Method Based on Local Masking and Multi-stage Momentum Optimization . (2026) : 329-341 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Adversarial examples have been a significant research focus since their discovery. Recent studies have applied watermarking and data hiding techniques to generate meaningful adversarial perturbations that carry specific information, further enriching the functionality of adversarial examples. However, these methods struggle to balance time complexity with attack efficacy. To address this issue, we propose the Gradient Masking Method (GMM), introducing a new perspective on generating meaningful perturbations. Unlike previous techniques that directly embed watermarks or data as adversarial distortions, GMM embeds information into adversarial perturbations by selectively blocking the updating noise at specific positions using a message mask encoded from the information. The resulting perturbations represent the binary sequence of the embedded message. This method enables processed images to exhibit adversarial properties while simultaneously serving as carriers of information. Experimental results demonstrate the efficacy of our approach. In terms of computational cost, our method significantly outperforms previous techniques without compromising attack effectiveness. We evaluated the attack success rate of the proposed method across seven widely used classifier models, comparing it with baseline and black-box attack methods. Results confirm that our method performs effectively in common attack scenarios influenced by the message mask. The code of GMM can be found at https://github.com/Abin110/Gradient-Masking_.
Keyword ：
Adversarial attacks Adversarial attacks Deep neural networks Deep neural networks Meaningful adversarial example Meaningful adversarial example
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Hanbin , Liao, Wenxing , Shu, Zhaogang et al. GMM: Efficient information-containing adversarial perturbation based on gradient masking method [J]. | INFORMATION FUSION , 2026 , 127 . |
| MLA | Lin, Hanbin et al. "GMM: Efficient information-containing adversarial perturbation based on gradient masking method" . | INFORMATION FUSION 127 (2026) . |
| APA | Lin, Hanbin , Liao, Wenxing , Shu, Zhaogang , Liu, Xiaolong . GMM: Efficient information-containing adversarial perturbation based on gradient masking method . | INFORMATION FUSION , 2026 , 127 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the rapid development of the Internet of Things (IoT), robust and secure authentication among interconnected devices has become increasingly significant. Existing cryptographic methods, despite their effectiveness, face challenges in scalability, quantum vulnerability, and high computational demands, which are particularly problematic for resource-constrained IoT devices. This paper proposes a novel and lightweight authentication scheme for IoT devices that combines the decentralization of blockchain with the efficiency of lattice-based cryptography to address these security concerns. The proposed scheme employs a decentralized identity management model built on blockchain, eliminating vulnerable central points and enhancing system resilience. For user and device authentication, an efficient lattice-based protocol is introduced, utilizing simplified hash operations and matrix-vector multiplication for key negotiation and authentication. This approach significantly reduces both computational complexity and communication overhead compared to traditional methods such as ECC-based schemes. Specifically, at a 100-bit security level, our scheme achieves authentication and key agreement in approximately 257.401 mu s and maintains a communication cost of 1052 bits per authentication session. Comprehensive performance analyses demonstrate that the proposed scheme can withstand typical cryptographic attacks and offers advantages in quantum computing resistance. Additionally, the blockchain-based design ensures high scalability, making the scheme ideal for large-scale IoT deployments without performance degradation. Experimental results further validate the scheme's practical applicability in resource-constrained IoT environments, highlighting its superior computational response times and lower communication costs compared to existing IoT authentication solutions.
Keyword ：
Blockchain Blockchain Internet of things (ioT) Internet of things (ioT) Lattice-based cryptography Lattice-based cryptography Lightweight authentication Lightweight authentication
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Kuang, Yingpan , Wu, Qiwen , Chen, Riqing et al. Blockchain based lightweight authentication scheme for internet of things using lattice encryption algorithm [J]. | COMPUTER STANDARDS & INTERFACES , 2025 , 93 . |
| MLA | Kuang, Yingpan et al. "Blockchain based lightweight authentication scheme for internet of things using lattice encryption algorithm" . | COMPUTER STANDARDS & INTERFACES 93 (2025) . |
| APA | Kuang, Yingpan , Wu, Qiwen , Chen, Riqing , Liu, Xiaolong . Blockchain based lightweight authentication scheme for internet of things using lattice encryption algorithm . | COMPUTER STANDARDS & INTERFACES , 2025 , 93 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Incident response plays a pivotal role in mitigating the impact of cyber attacks. In recent years, the intensity and complexity of global cyber threats have grown significantly, making it increasingly challenging for traditional threat detection and incident response methods to operate effectively in complex network environments. While Large Language Models (LLMs) have shown great potential in early threat detection, their capabilities remain limited when it comes to automated incident response after an intrusion. To address this gap, we construct an incremental benchmark based on real-world incident response tasks to thoroughly evaluate the performance of LLMs in this domain. Our analysis reveals several key challenges that hinder the practical application of contemporary LLMs, including context loss, hallucinations, privacy protection concerns, and their limited ability to provide accurate, context-specific recommendations. In response to these challenges, we propose IRCopilot, a novel framework for automated incident response powered by LLMs. IRCopilot mimics the three dynamic phases of a real-world incident response team using four collaborative LLM-based session components. These components are designed with clear divisions of responsibility, reducing issues such as hallucinations and context loss. Our method leverages diverse prompt designs and strategic responsibility segmentation, significantly improving the system’s practicality and efficiency. Experimental results demonstrate that IRCopilot outperforms baseline LLMs across key benchmarks, achieving sub-task completion rates of 150%, 138%, 136%, 119%, and 114% for various response tasks. Moreover, IRCopilot exhibits robust performance on public incident response platforms and in real-world attack scenarios, showcasing its strong applicability. Copyright © 2025, The Authors. All rights reserved.
Keyword ：
Automation Automation Benchmarking Benchmarking Complex networks Complex networks Computer crime Computer crime Distributed computer systems Distributed computer systems Intrusion detection Intrusion detection Network security Network security
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Xihuan , Zhang, Jie , Deng, Gelei et al. IRCopilot: Automated Incident Response with Large Language Models [J]. | arXiv , 2025 . |
| MLA | Lin, Xihuan et al. "IRCopilot: Automated Incident Response with Large Language Models" . | arXiv (2025) . |
| APA | Lin, Xihuan , Zhang, Jie , Deng, Gelei , Liu, Tianzhe , Liu, Xiaolong , Yang, Changcai et al. IRCopilot: Automated Incident Response with Large Language Models . | arXiv , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The widespread convenience of generative models has exacerbated the misuse of attribute-editing-based Deepfake technologies, leading to the proliferation of illegally generated content that severely threatens personal privacy and security. Existing proactive defense strategies mitigate Deepfake attacks by embedding imperceptible adversarial watermarks into the spatial-domain of protected images. However, spatial-domain adversarial watermarks are inherently sensitive to lossy compression operations, which significantly degrades their defense efficacy. To address this limitation, we propose a frequency-domain cross-image adversarial watermark generation scheme to enhance robustness toward JPEG compression. In the proposed method, the adversarial watermark training process is migrated to the frequency domain using a differentiable JPEG module, which explicitly simulates the impact of quantization and compression on perturbation distributions. Furthermore, a fusion module is incorporated to coordinate watermark distributions across images, thereby enhancing the generalization of the defense. Experimental results demonstrate that the generated adversarial watermarks exhibit strong robustness against JPEG compression and effectively disrupt the outputs of Deepfake models. Moreover, the proposed scheme can be directly applied to diverse facial images without retraining, thereby providing reliable protection for real-world image application scenarios.
Keyword ：
Adversarial attack Adversarial attack Cross-image Cross-image Deepfake Deepfake JPEG-resistance JPEG-resistance Proactive defense Proactive defense
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Zhiyu , Lin, Hanbin , Lin, Liqiang et al. Robust cross-image adversarial watermark with JPEG resistance for defending against Deepfake models [J]. | COMPUTER VISION AND IMAGE UNDERSTANDING , 2025 , 260 . |
| MLA | Lin, Zhiyu et al. "Robust cross-image adversarial watermark with JPEG resistance for defending against Deepfake models" . | COMPUTER VISION AND IMAGE UNDERSTANDING 260 (2025) . |
| APA | Lin, Zhiyu , Lin, Hanbin , Lin, Liqiang , Chen, Shuwu , Liu, Xiaolong . Robust cross-image adversarial watermark with JPEG resistance for defending against Deepfake models . | COMPUTER VISION AND IMAGE UNDERSTANDING , 2025 , 260 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the advancement of information technology, video data have become a primary source of information on the internet, shaping public perception. However, maliciously tampered videos pose a serious threat to social trust, highlighting the necessity for video authentication. This study focuses on the detection of video frame deletion manipulation. Although existing frame deletion forensic methods have achieved remarkable progress, most rely solely on visual data, limiting their performances in complex scenarios. To address this limitation, we propose a novel framework, TMTC (Trustworthy Multimodal Transformer Classification), which integrates both audio and visual features for improved detection performance. Specifically, the framework leverages an enhanced ResNet to extract audio features and a three-dimensional convolutional neural network (3DCNN) to capture visual features. The multimodal fusion method, which is based on uncertainty, may yield conflicts in confidence levels during the feature fusion process. To facilitate effective multimodal fusion, we propose a cross-modal feature mediation (CFM) module that addresses modality-specific confidence bias and resolves inter-modal discrepancies, including temporal misalignment and feature inconsistency. Finally, a Dempster-Shafer evidence theory module is utilized for robust classification. Experimental results show that TMTC achieves a 1.48% accuracy improvement on non-degraded datasets and a 5.43% improvement on noisy datasets, compared to the best-performing method among the state-of-the-art frame deletion detection techniques evaluated.
Keyword ：
Deep learning Deep learning Dempster-Shafer evidence theory Dempster-Shafer evidence theory Digital video forensics Digital video forensics Frame deletion detection Frame deletion detection Multi-modal Multi-modal Multimodal uncertainty modeling Multimodal uncertainty modeling
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Feng, Chunhui , Zhong, Yongxiang , Huang, Yigong et al. TMTC: trusted multi-modal transformer classification framework for video frame deletion detection [J]. | JOURNAL OF SUPERCOMPUTING , 2025 , 81 (7) . |
| MLA | Feng, Chunhui et al. "TMTC: trusted multi-modal transformer classification framework for video frame deletion detection" . | JOURNAL OF SUPERCOMPUTING 81 . 7 (2025) . |
| APA | Feng, Chunhui , Zhong, Yongxiang , Huang, Yigong , Liu, Xiaolong . TMTC: trusted multi-modal transformer classification framework for video frame deletion detection . | JOURNAL OF SUPERCOMPUTING , 2025 , 81 (7) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Deep learning-based steganography techniques utilizing generative adversarial networks have attracted considerable attention due to their ability to produce realistic images that serve as effective carriers for hidden information. However, as the capacity for embedding information increases, the quality of the generated covert images tends to decline significantly. To address these challenges and enhance both the quality of covert images and data-hiding performance, we propose a high-capacity image steganography method known as Multi-Target Adversarial Image Steganography (MTAIS). This method leverages a multi-target adversarial attack technique to effectively conceal high-capacity secret information within images. The proposed scheme adapts the fully connected layer of the recognition model and transforms the undirected adversarial attack into a directed adversarial attack targeting multiple outputs, allowing for fine-tuning of the base model without extensive retraining. We conducted comprehensive experiments to benchmark the proposed scheme against several established deep learning-based steganography schemes. The results indicate that the proposed scheme consistently outperforms its competitors across various evaluation metrics. Notably, our method preserves the quality of the cover image, ensuring visual integrity while achieving a high capacity for embedding secret information. The experimental results underscore the advantages of the proposed scheme in terms of performance and efficiency, establishing it as a robust solution for high-capacity image steganography.
Keyword ：
Adversarial attack Adversarial attack Deep learning Deep learning Multi-target adversarial attack Multi-target adversarial attack Steganography Steganography
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Xiaolong , Shen, Minghuang , Liu, Jiayi et al. Image steganography with high embedding capacity based on multi-target adversarial attack [J]. | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2025 , 156 . |
| MLA | Liu, Xiaolong et al. "Image steganography with high embedding capacity based on multi-target adversarial attack" . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 156 (2025) . |
| APA | Liu, Xiaolong , Shen, Minghuang , Liu, Jiayi , Wu, Qiwen . Image steganography with high embedding capacity based on multi-target adversarial attack . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2025 , 156 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Invisible watermarking is widely used for tracking and holding accountable unauthorized usage of copyrighted content, but it does not prevent attackers from obtaining illegal access to digital assets. Consequently, user privacy and security are significantly compromised. Recent investigations have revealed that adversarial attacks are capable of misleading state-of-the-art deep learning models by inducing incorrect classifications. The generated adversarial examples can dramatically mitigate malicious access to protected content. To integrate invisible watermarking with adversarial attacks in a unified task, we explore the potential of creating meaningful perturbations in adversarial examples that combine adversarial attacks with secure watermark perturbations. A novel method called ISWP (invisible and secure watermark perturbations) for embedding meaningful perturbations into input images is proposed in this paper to accomplish both adversarial attacks and copyright protection. ISWP employs the discrete wavelet transform (DWT) and basin hopping (BH) in its adversarial attack process, resulting in the creation of imperceptible adversarial watermark perturbations. Furthermore, encryption technologies are incorporated into the adversarial attack process to safeguard against unauthorized malicious access. The experimental results show that the generated adversarial examples exhibit benign visual performance while achieving remarkable attack capacity and robustness on different DNN models, and the embedded watermarks are extracted as powerful tools for copyright certification, which demonstrates their effectiveness as a protection mechanism for private content.
Keyword ：
Adversarial attack Adversarial attack Adversarial examples Adversarial examples Basin hopping Basin hopping Copyright protection Copyright protection Invisible watermark Invisible watermark
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liang, Jinchao , Liu, Yang , Gao, Lu et al. ISWP: Novel high-fidelity adversarial examples generated by incorporating invisible and secure watermark perturbations [J]. | APPLIED INTELLIGENCE , 2025 , 55 (1) . |
| MLA | Liang, Jinchao et al. "ISWP: Novel high-fidelity adversarial examples generated by incorporating invisible and secure watermark perturbations" . | APPLIED INTELLIGENCE 55 . 1 (2025) . |
| APA | Liang, Jinchao , Liu, Yang , Gao, Lu , Zhang, Ze , Liu, Xiaolong . ISWP: Novel high-fidelity adversarial examples generated by incorporating invisible and secure watermark perturbations . | APPLIED INTELLIGENCE , 2025 , 55 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
设计了可兼容大部分眼动仪的教学视频眼动分析系统,并从眼动数据记录、动态兴趣区定义、眼动分析 3个模块,探讨了教学视频眼动分析系统的实现机制.该系统有助于提高眼动分析在教育领域应用的普适性,降低研究者在眼动相关方向的研究成本.
Keyword ：
教学视频 教学视频 数据分析 数据分析 眼动分析 眼动分析 眼动追踪 眼动追踪 视频分析 视频分析
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 柳晓龙 , 钟节辉 . 基于眼动追踪技术的教学视频眼动分析系统 [J]. | 河南教育学院学报（自然科学版） , 2024 , 33 (1) : 26-31 . |
| MLA | 柳晓龙 et al. "基于眼动追踪技术的教学视频眼动分析系统" . | 河南教育学院学报（自然科学版） 33 . 1 (2024) : 26-31 . |
| APA | 柳晓龙 , 钟节辉 . 基于眼动追踪技术的教学视频眼动分析系统 . | 河南教育学院学报（自然科学版） , 2024 , 33 (1) , 26-31 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
数字图像在云环境下的安全性问题已成为信息安全领域的研究热点之一。为解决传统密文域可逆信息隐藏算法缺乏伪装性，容易受到恶意攻击与信息隐藏空间容量小的问题，提出了基于图像伪装加密与双向差值扩展的大容量密文域可逆信息隐藏算法。该算法首先利用矢量量化与离散小波变换两种技术对原始图像进行伪装加密，从而保证隐蔽性，使得图像在云环境中安全传递；其次采用基于双向差值扩展的信息隐藏技术对伪装加密图像进行秘密信息的嵌入，以实现高容量的信息隐藏。实验结果表明，所提算法不仅实现了图像伪装，而且最终得到的含密伪装图像与原始图像在视觉上无明显差别，峰值信噪比达到40 dB以上，对原始图像起到了很好的伪装效果；同时实现了高容量的秘密信息嵌入，图像平均嵌入率接近0.6 bpp,表现出了良好的实验性能。
Keyword ：
信息隐藏 信息隐藏 图像伪装 图像伪装 差值扩展 差值扩展 矢量量化 矢量量化 离散小波变换 离散小波变换
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 廖文兴 , 刘成语 , 林松 et al. 基于图像伪装与双向差值扩展的密文域可逆信息隐藏算法 [J]. | 计算机应用研究 , 2024 , 41 (02) : 596-601 . |
| MLA | 廖文兴 et al. "基于图像伪装与双向差值扩展的密文域可逆信息隐藏算法" . | 计算机应用研究 41 . 02 (2024) : 596-601 . |
| APA | 廖文兴 , 刘成语 , 林松 , 柳晓龙 . 基于图像伪装与双向差值扩展的密文域可逆信息隐藏算法 . | 计算机应用研究 , 2024 , 41 (02) , 596-601 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
