Zhihong Tian

Yixiao Xu, Binxing Fang, Rui Wang et al.

Developing high-performance deep learning models is resource-intensive, leading model owners to utilize Machine Learning as a Service (MLaaS) platforms instead of publicly releasing their models. However, malicious users may exploit query interfaces to execute model extraction attacks, reconstructing the target model's functionality locally. While prior research has investigated triggerable watermarking techniques for asserting ownership, existing methods face significant challenges: (1) most approaches require additional training, resulting in high overhead and limited flexibility, and (2) they often fail to account for advanced attackers, leaving them vulnerable to adaptive attacks. In this paper, we propose Neural Honeytrace, a robust plug-and-play watermarking framework against model extraction attacks. We first formulate a watermark transmission model from an information-theoretic perspective, providing an interpretable account of the principles and limitations of existing triggerable watermarking. Guided by the model, we further introduce: (1) a similarity-based training-free watermarking method for plug-and-play and flexible watermarking, and (2) a distribution-based multi-step watermark information transmission strategy for robust watermarking. Comprehensive experiments on four datasets demonstrate that Neural Honeytrace outperforms previous methods in efficiency and resisting adaptive attacks. Neural Honeytrace reduces the average number of samples required for a worst-case t-Test-based copyright claim from 193,252 to 1,857 with zero training cost. The code is available at https://github.com/NeurHT/NeurHT.

Keke Tang, Weiyao Ke, Weilong Peng et al.

Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challenging to balance imperceptibility with adversarial effectiveness. In this paper, we attribute the inadequate imperceptibility of adversarial attacks on point clouds to deviations from the underlying surface. To address this, we introduce a novel point-to-surface (P2S) field that adjusts adversarial perturbation directions by dragging points back to their original underlying surface. Specifically, we use a denoising network to learn the gradient field of the logarithmic density function encoding the shape's surface, and apply a distance-aware adjustment to perturbation directions during attacks, thereby enhancing imperceptibility. Extensive experiments show that adversarial attacks guided by our P2S field are more imperceptible, outperforming state-of-the-art methods.

Lei Zhang, Shuaimin Jiang, Xiajiong Shen et al.

With the continuous development of industrial IoT (IIoT) technology, network security is becoming more and more important. And intrusion detection is an important part of its security. However, since the amount of attack traffic is very small compared to normal traffic, this imbalance makes intrusion detection in it very difficult. To address this imbalance, an intrusion detection system called pretraining Wasserstein generative adversarial network intrusion detection system (PWG-IDS) is proposed in this paper. This system is divided into two main modules: 1) In this module, we introduce the pretraining mechanism in the Wasserstein generative adversarial network with gradient penalty (WGAN-GP) for the first time, firstly using the normal network traffic to train the WGAN-GP, and then inputting the imbalance data into the pre-trained WGAN-GP to retrain and generate the final required data. 2) Intrusion detection module: We use LightGBM as the classification algorithm to detect attack traffic in IIoT networks. The experimental results show that our proposed PWG-IDS outperforms other models, with F1-scores of 99% and 89% on the 2 datasets, respectively. And the pretraining mechanism we proposed can also be widely used in other GANs, providing a new way of thinking for the training of GANs.

Bin Zhu, Zhaoquan Gu, Le Wang et al.

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection methods usually make assumptions about the adversarial example and attack method (e.g., the word frequency of the adversarial example, the perturbation level of the attack method). However, this limits the applicability of the detection method. To this end, we propose TREATED, a universal adversarial detection method that can defend against attacks of various perturbation levels without making any assumptions. TREATED identifies adversarial examples through a set of well-designed reference models. Extensive experiments on three competitive neural networks and two widely used datasets show that our method achieves better detection performance than baselines. We finally conduct ablation studies to verify the effectiveness of our method.

Xugong Qin, Yu Zhou, Youhui Guo et al.

Due to the large success in object detection and instance segmentation, Mask R-CNN attracts great attention and is widely adopted as a strong baseline for arbitrary-shaped scene text detection and spotting. However, two issues remain to be settled. The first is dense text case, which is easy to be neglected but quite practical. There may exist multiple instances in one proposal, which makes it difficult for the mask head to distinguish different instances and degrades the performance. In this work, we argue that the performance degradation results from the learning confusion issue in the mask head. We propose to use an MLP decoder instead of the "deconv-conv" decoder in the mask head, which alleviates the issue and promotes robustness significantly. And we propose instance-aware mask learning in which the mask head learns to predict the shape of the whole instance rather than classify each pixel to text or non-text. With instance-aware mask learning, the mask branch can learn separated and compact masks. The second is that due to large variations in scale and aspect ratio, RPN needs complicated anchor settings, making it hard to maintain and transfer across different datasets. To settle this issue, we propose an adaptive label assignment in which all instances especially those with extreme aspect ratios are guaranteed to be associated with enough anchors. Equipped with these components, the proposed method named MAYOR achieves state-of-the-art performance on five benchmarks including DAST1500, MSRA-TD500, ICDAR2015, CTW1500, and Total-Text.

Keke Tang, Dingruibo Miao, Weilong Peng et al.

Overconfident predictions on out-of-distribution (OOD) samples is a thorny issue for deep neural networks. The key to resolve the OOD overconfidence issue inherently is to build a subset of OOD samples and then suppress predictions on them. This paper proposes the Chamfer OOD examples (CODEs), whose distribution is close to that of in-distribution samples, and thus could be utilized to alleviate the OOD overconfidence issue effectively by suppressing predictions on them. To obtain CODEs, we first generate seed OOD examples via slicing&splicing operations on in-distribution samples from different categories, and then feed them to the Chamfer generative adversarial network for distribution transformation, without accessing to any extra data. Training with suppressing predictions on CODEs is validated to alleviate the OOD overconfidence issue largely without hurting classification accuracy, and outperform the state-of-the-art methods. Besides, we demonstrate CODEs are useful for improving OOD detection and classification.

Keke Tang, Peng Song, Yuexin Ma et al.

High-level (e.g., semantic) features encoded in the latter layers of convolutional neural networks are extensively exploited for image classification, leaving low-level (e.g., color) features in the early layers underexplored. In this paper, we propose a novel Decision Propagation Module (DPM) to make an intermediate decision that could act as category-coherent guidance extracted from early layers, and then propagate it to the latter layers. Therefore, by stacking a collection of DPMs into a classification network, the generated Decision Propagation Network is explicitly formulated as to progressively encode more discriminative features guided by the decision, and then refine the decision based on the new generated features layer by layer. Comprehensive results on four publicly available datasets validate DPM could bring significant improvements for existing classification networks with minimal additional computational cost and is superior to the state-of-the-art methods.

Zhihong Tian, Xiangsong Gao, Shen Su et al.

Conducting reputation management is very important for Internet of vehicles. However, most of the existing researches evaluate the effectiveness of their schemes with settled attacking behaviors in their simulation which cannot represent the scenarios in reality. In this paper, we propose to consider dynamical and diversity attacking strategies in the simulation of reputation management scheme evaluation. To that end, we apply evolutionary game theory to model the evolution process of malicious users' attacking strategies, and discuss the methodology of the evaluation simulations. We further apply our evaluation method to a reputation management scheme with multiple utility functions, and discuss the evaluation results. The results indicate that our evaluation method is able to depict the evolving process of the dynamic attacking strategies in a vehicular network, and the final state of the simulation could be used to quantify the protection effectiveness of the reputation management scheme.

Zhihong Tian, Wei Shi, Yuhang Wang et al.

Edge computing is providing higher class intelligent service and computing capabilities at the edge of the network. The aim is to ease the backhaul impacts and offer an improved user experience, however, the edge artificial intelligence exacerbates the security of the cloud computing environment due to the dissociation of data, access control and service stages. In order to prevent users from using the edge-cloud computing environment to carry out lateral movement attacks, we proposed a method named CloudSEC meaning real time lateral movement detection based on evidence reasoning network for the edge-cloud environment. The concept of vulnerability correlation is introduced. Based on the vulnerability knowledge and environmental information of the network system, the evidence reasoning network is constructed, and the lateral movement reasoning ability provided by the evidence reasoning network is used. CloudSEC realizes the reconfiguration of the efficient real-time attack process. The experiment shows that the results are complete and credible.