Shifeng Ni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shifeng Ni has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Mingfu Xue
School of Communication and Electronic Engineering, East China Normal University, Shanghai, China
4 shared publications - Weiqiang Liu
Nanjing University of Aeronautics and Astronautics
4 shared publications - Yushu Zhang
Jiangxi University of Finance and Economics
4 shared publications - Leo Yu Zhang
School of Information and Communication Technology, Griffith University, Southport, Queensland, Australia
3 shared publications - Yinghao Wu
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
3 shared publications Heyi Wu
Sangfor Technologies Inc., Nanjing, China
1 shared publication
Latest Publications
- 15 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 14 (4) , 743-757
A Reinforcement Learning-Based ELF Adversarial Malicious Sample Generation Method
In recent years, domestic Linux operating systems have developed rapidly, but the threat of ELF viruses has become increasingly prominent. Currently, domestic antivirus software for information technology application innovation (ITAI) operating systems shows insufficient capability in detecting ELF viruses. At the same time, research on generating malicious samples in ELF format is scarce. In order to fill this gap at home and abroad and meet the growing application needs of domestic antivirus software companies, this paper proposes an automatic ELF adversarial malicious samples generation technique based on reinforcement learning. Based on reinforcement learning framework, after being processed by cycles of feature extraction, malicious detection, agent decision-making, and evade-detection operation, the sample can evade the detection of antivirus engines. Specifically, nine feature extractor subclasses are used to extract features in multiple aspects. The PPO algorithm is used as the agent algorithm. The action table in the evade-detection module contains 11 evade-detection operations for ELF malicious samples. This method is experimentally verified on the ITAI operating system, and the ELF malicious sample set on the Linux x86 platform is used as the original sample set. The detection rate of this sample set by ClamAV before processing is 98%, and the detection rate drops to 25% after processing. The detection rate of this sample set by 360 Security before processing is 4%, and the detection rate drops to 1% after processing. Furthermore, after processing, the average number of engines on VirusTotal that could detect the maliciousness of the sample decreases from 39 to 15. Many malicious samples were detected by 41~43 engines on VirusTotal before processing, while after the evade-detection processing, only 8~9 engines on VirusTotal can detect the malware. In terms of executability and malicious function consistency, the processed samples can still run normally and the malicious functions remain consistent with those before processing. Overall, the proposed method in this paper can effectively generate adversarial ELF malware samples. Using this method to generate malicious samples to test and train the anti-virus software can promote and improve anti-virus software’s detection and defense capability against malware.
- 15 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 14 (4) , 743-757
A Reinforcement Learning-Based ELF Adversarial Malicious Sample Generation Method
In recent years, domestic Linux operating systems have developed rapidly, but the threat of ELF viruses has become increasingly prominent. Currently, domestic antivirus software for information technology application innovation (ITAI) operating systems shows insufficient capability in detecting ELF viruses. At the same time, research on generating malicious samples in ELF format is scarce. In order to fill this gap at home and abroad and meet the growing application needs of domestic antivirus software companies, this paper proposes an automatic ELF adversarial malicious samples generation technique based on reinforcement learning. Based on reinforcement learning framework, after being processed by cycles of feature extraction, malicious detection, agent decision-making, and evade-detection operation, the sample can evade the detection of antivirus engines. Specifically, nine feature extractor subclasses are used to extract features in multiple aspects. The PPO algorithm is used as the agent algorithm. The action table in the evade-detection module contains 11 evade-detection operations for ELF malicious samples. This method is experimentally verified on the ITAI operating system, and the ELF malicious sample set on the Linux x86 platform is used as the original sample set. The detection rate of this sample set by ClamAV before processing is 98%, and the detection rate drops to 25% after processing. The detection rate of this sample set by 360 Security before processing is 4%, and the detection rate drops to 1% after processing. Furthermore, after processing, the average number of engines on VirusTotal that could detect the maliciousness of the sample decreases from 39 to 15. Many malicious samples were detected by 41~43 engines on VirusTotal before processing, while after the evade-detection processing, only 8~9 engines on VirusTotal can detect the malware. In terms of executability and malicious function consistency, the processed samples can still run normally and the malicious functions remain consistent with those before processing. Overall, the proposed method in this paper can effectively generate adversarial ELF malware samples. Using this method to generate malicious samples to test and train the anti-virus software can promote and improve anti-virus software’s detection and defense capability against malware.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (9) , 4649-4659
An Explainable Intellectual Property Protection Method for Deep Neural Networks Based on Intrinsic Features
Intellectual property (IP) protection for Deep Neural Networks (DNNs) has raised serious concerns in recent years. Most existing works embed watermarks in the DNN model for IP protection, which need to modify the model and do not consider/mention interpretability. In this paper, for the first time, we propose an interpretable intellectual property protection method for DNN based on explainable artificial intelligence. Compared with existing works, the proposed method does not modify the DNN model, and the decision of the ownership verification is interpretable. We extract the intrinsic features of the DNN model by using Deep Taylor Decomposition. Since the intrinsic feature is composed of unique interpretation of the model’s decision, the intrinsic feature can be regarded as fingerprint of the model. If the fingerprint of a suspected model is the same as the original model, the suspected model is considered as a pirated model. Experimental results demonstrate that the fingerprints can be successfully used to verify the ownership of the model and the test accuracy of the model is not affected. Furthermore, the proposed method is robust to fine-tuning attack, pruning attack, watermark overwriting attack, and adaptive attack.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (9) , 4649-4659
An Explainable Intellectual Property Protection Method for Deep Neural Networks Based on Intrinsic Features
Intellectual property (IP) protection for Deep Neural Networks (DNNs) has raised serious concerns in recent years. Most existing works embed watermarks in the DNN model for IP protection, which need to modify the model and do not consider/mention interpretability. In this paper, for the first time, we propose an interpretable intellectual property protection method for DNN based on explainable artificial intelligence. Compared with existing works, the proposed method does not modify the DNN model, and the decision of the ownership verification is interpretable. We extract the intrinsic features of the DNN model by using Deep Taylor Decomposition. Since the intrinsic feature is composed of unique interpretation of the model’s decision, the intrinsic feature can be regarded as fingerprint of the model. If the fingerprint of a suspected model is the same as the original model, the suspected model is considered as a pirated model. Experimental results demonstrate that the fingerprints can be successfully used to verify the ownership of the model and the test accuracy of the model is not affected. Furthermore, the proposed method is robust to fine-tuning attack, pruning attack, watermark overwriting attack, and adaptive attack.
- 29 December 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (1) , 1099-1116
Imperceptible and multi-channel backdoor attack
- 29 December 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (1) , 1099-1116
Imperceptible and multi-channel backdoor attack
- 20 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (3) , 5004-5013
Untargeted Backdoor Attack Against Deep Neural Networks With Imperceptible Trigger
Recent research works have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks. The existing backdoor attacks can only cause targeted misclassification on backdoor instances, which makes them can be easily detected by defense methods. In this article, we propose an untargeted backdoor attack (UBA) against DNNs, where the backdoor instances are randomly misclassified by the backdoored model to any incorrect label. To achieve the goal of UBA, we propose to utilize autoencoder as the trigger generation model and train the target model and the autoencoder simultaneously. We also propose a special loss function (Evasion Loss) to train the autoencoder and the target model, in order to make the target model predict backdoor instances as random incorrect classes. During the inference stage, the trained autoencoder is used to generate backdoor instances. For different backdoor instances, the generated triggers are different and the corresponding predicted labels are random incorrect labels. Experimental results demonstrate that the proposed UBA is effective. On the ResNet-18 model, the attack success rate (ASR) of the proposed UBA is 96.48%, 91.27%, and 90.83% on CIFAR-10, GTSRB, and ImageNet datasets, respectively. On the VGG-16 model, the ASR of the proposed UBA is 89.72% and 97.78% on CIFAR-10 and ImageNet datasets, respectively. Moreover, the proposed UBA is robust against existing backdoor defense methods, which are designed to detect targeted backdoor attacks. We hope this article can promote the research of corresponding backdoor defense works.
- 20 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (3) , 5004-5013
Untargeted Backdoor Attack Against Deep Neural Networks With Imperceptible Trigger
Recent research works have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks. The existing backdoor attacks can only cause targeted misclassification on backdoor instances, which makes them can be easily detected by defense methods. In this article, we propose an untargeted backdoor attack (UBA) against DNNs, where the backdoor instances are randomly misclassified by the backdoored model to any incorrect label. To achieve the goal of UBA, we propose to utilize autoencoder as the trigger generation model and train the target model and the autoencoder simultaneously. We also propose a special loss function (Evasion Loss) to train the autoencoder and the target model, in order to make the target model predict backdoor instances as random incorrect classes. During the inference stage, the trained autoencoder is used to generate backdoor instances. For different backdoor instances, the generated triggers are different and the corresponding predicted labels are random incorrect labels. Experimental results demonstrate that the proposed UBA is effective. On the ResNet-18 model, the attack success rate (ASR) of the proposed UBA is 96.48%, 91.27%, and 90.83% on CIFAR-10, GTSRB, and ImageNet datasets, respectively. On the VGG-16 model, the ASR of the proposed UBA is 89.72% and 97.78% on CIFAR-10 and ImageNet datasets, respectively. Moreover, the proposed UBA is robust against existing backdoor defense methods, which are designed to detect targeted backdoor attacks. We hope this article can promote the research of corresponding backdoor defense works.