Bingbing Song

Bingbing Song

Auto-generated profile, based on publicly available information

Bingbing Song

National Pilot School of Software, Yunnan University, Kunming, 650504, Yunnan, China; School of Information Science and Engineering, Yunnan University, Kunming, 650504, Yunnan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 June 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
BSBingbing Song
Bingbing Song
PWPing Wei
Ping Wei
SWSixing Wu
Sixing Wu
YLYu Lin
Yu Lin
WZWei Zhou
Wei Zhou

16 November 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
JZJiabao Zhou
Jiabao Zhou
JZJinhong Zhang
Jinhong Zhang
WZWei Zhou
Wei Zhou
CYChao Yi
Chao Yi
BSBingbing Song
Bingbing Song

4 March 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
SGSong Gao
Song Gao
XWXiaoxuan Wang
Xiaoxuan Wang
BSBingbing Song
Bingbing Song
RLRenyang Liu
Renyang Liu
SYShaowen Yao
Shaowen Yao
SYShui Yu
Shui Yu
Deep neural networks (DNNs) are sensitive to adversarial examples which are generated by corrupting benign examples with imperceptible perturbations, or have significant changes but can still achieve original prediction results. The latter case is termed as the Type I adversarial example which, however, has limited attention in the literature. In this paper, we introduce two methods, termed HRG and GAG, to generate Type I adversarial examples and attempt to apply them to the privacy-preserving Machine Learning as a Service (MLaaS). Existing methods for the privacy-preserving MLaaS are mostly based on cryptographic techniques, which often incur additional communication and computation overhead, while using Type I adversarial examples to hide users' privacy data is a brand-new exploration. Specifically, HRG utilizes the high-level representations of DNNs to guide generators, and GAG leverages the generative adversarial network to transform original images. Our solution does not involve any model modifications and allows DNNs to run directly on transformed data, thus arousing no additional communication and computation overhead. Extensive experiments on MNIST, CIFAR-10, and ImageNet show that HRG can perfectly hide images into noise and achieve similar accuracy as the original accuracy, and GAG can generate natural images that are completely different from the original images with a small loss of accuracy.

10 October 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
BSBingbing Song
Bingbing Song
RWRuxin Wang
Ruxin Wang
WHWei He
Wei He
WZWei Zhou
Wei Zhou
Adversarial examples easily mislead vision systems based on deep neural networks (DNNs) trained with softmax cross entropy (SCE) loss. The vulnerability of DNN comes from the fact that SCE drives DNNs to fit on the training examples, whereas the resultant feature distributions between the training and adversarial examples are unfortunately misaligned. Several state-of-the-art methods start from improving the inter-class separability of training examples by modifying loss functions, where we argue that the adversarial examples are ignored, thus resulting in a limited robustness to adversarial attacks. In this paper, we exploited the inference region, which inspired us to apply margin-like inference information to SCE, resulting in a novel inference-softmax cross entropy (I-SCE) loss, which is intuitively appealing and interpretable. The inference information guarantees that it is difficult for neural networks to cross the decision boundary under an adversarial attack, and guarantees both the inter-class separability and the improved generalization to adversarial examples, which was further demonstrated and proved under the min-max framework. Extensive experiments show that the DNN models trained with the proposed I-SCE loss achieve a superior performance and robustness over the state-of-the-arts under different prevalent adversarial attacks; for example, the accuracy of I-SCE is 63% higher than SCE under the PGD50un attack on the MNIST dataset. These experiments also show that the inference region can effectively solve the misaligned distribution.

15 June 2023 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
BSBingbing Song
Bingbing Song
Ruxin WangRuxin Wang
Ruxin Wang
SGSong Gao
Song Gao
YDYunyun Dong
Yunyun Dong
LLLing Liu
Ling Liu
WZWei Zhou
Wei Zhou
Most cloud providers offer Deep Learning as a Service (DLaaS) for different business, science and engineering domains. However, it is known that deep neural networks (DNNs) are vulnerable to adversarial examples, which can cause well-trained DNN models to misbehave by injecting human-imperceptible perturbations to the query input data. Securing deep learning as a service becomes a critical challenge in mitigating such adversarial input perturbations, and enhancing the robustness of DNNs. In this paper, we report two important facts: First, most adversarial perturbations are high frequency signals or are added to high frequency signals. Second, due to Frequency Principle that neural networks overly pay attention to fit the low frequency signals during training, the models could be easily misled by the high frequency signals of adversarial examples. These facts consequently contribute to the vulnerability of DNNs service in the Cloud. We conjecture that the more robust the neural networks are in learning from high frequency signals, the more resilient these neural networks are against adversarial perturbed examples. We propose a novel method for generating high-frequency-enhanced adversarial examples, which is achieved by a high-pass filter in the frequency domain via Fourier Transform. This method enhances the learning ability for high frequency signals and ameliorates to over-fit useless low frequency signals. In order to improve the robustness of DNNs service under such signal frequency attacks, we propose a multi-modal collaborative adversarial training framework, named as MMCAT, which uses the multi-modal information of the input images for cross-modal collaborative training, delivering excellent extension for effectively learning of multi-modal image information. Extensive experiments show that under strong adaptive frequency attacks, the DNNs service trained with the proposed MMCAT method achieve superior performance and robustness over the state-of-the-art adversarial training approaches.

21 January 2026 in Neural Networks
Verified
Journal Article
Closed access
ZLZongxin Liu
Zongxin Liu
JZJinhong Zhang
Jinhong Zhang
YDYunyun Dong
Yunyun Dong
BSBingbing Song
Bingbing Song
WZWei Zhou
Wei Zhou