Rui Zhang

Jian Liu, Rui Zhang, Sebastian Szyller et al.

Deep neural network (DNN) models are valuable intellectual property of model owners, constituting a competitive advantage. Therefore, it is crucial to develop techniques to protect against model theft. Model ownership resolution (MOR) is a class of techniques that can deter model theft. A MOR scheme enables an accuser to assert an ownership claim for a suspect model by presenting evidence, such as a watermark or fingerprint, to show that the suspect model was stolen or derived from a source model owned by the accuser. Most of the existing MOR schemes prioritize robustness against malicious suspects, ensuring that the accuser will win if the suspect model is indeed a stolen model. In this paper, we show that common MOR schemes in the literature are vulnerable to a different, equally important but insufficiently explored, robustness concern: a malicious accuser. We show how malicious accusers can successfully make false claims against independent suspect models that were not stolen. Our core idea is that a malicious accuser can deviate (without detection) from the specified MOR process by finding (transferable) adversarial examples that successfully serve as evidence against independent suspect models. To this end, we first generalize the procedures of common MOR schemes and show that, under this generalization, defending against false claims is as challenging as preventing (transferable) adversarial examples. Via systematic empirical evaluation, we show that our false claim attacks always succeed in the MOR schemes that follow our generalization, including in a real-world model: Amazon's Rekognition API.

Le Peng, Yash Travadi, Rui Zhang et al.

We propose performing imbalanced classification by regrouping majority classes into small classes so that we turn the problem into balanced multiclass classification. This new idea is dramatically different from popular loss reweighting and class resampling methods. Our preliminary result on imbalanced medical image classification shows that this natural idea can substantially boost the classification performance as measured by average precision (approximately area-under-the-precision-recall-curve, or AUPRC), which is more appropriate for evaluating imbalanced classification than other metrics such as balanced accuracy.

Hui Xia, Xiugui Yang, Xiangyun Qian et al.

During the generation of invisible backdoor attack poisoned data, the feature space transformation operation tends to cause the loss of some poisoned features and weakens the mapping relationship between source images with triggers and target labels, resulting in the need for a higher poisoning rate to achieve the corresponding backdoor attack success rate. To solve the above problems, we propose the idea of feature repair for the first time and introduce the blind watermark technique to repair the poisoned features lost during the generation of poisoned data. Under the premise of ensuring consistent labeling, we propose a low-poisoning rate invisible backdoor attack based on feature repair, named FRIB. Benefiting from the above design concept, the new method enhances the mapping relationship between the source images with triggers and the target labels, and increases the degree of misleading DNNs, thus achieving a high backdoor attack success rate with a very low poisoning rate. Ultimately, the detailed experimental results show that the goal of achieving a high success rate of backdoor attacks with a very low poisoning rate is achieved on all MNIST, CIFAR10, GTSRB, and ImageNet datasets.

Hui Xia, Rui Zhang, Shuliang Jiang et al.

Black-box attacks usually face two problems: poor transferability and the inability to evade the adversarial defense. To overcome these shortcomings, we create an original approach to generate adversarial examples by smoothing the linear structure of the texture in the benign image, called AdvSmo. We construct the adversarial examples without relying on any internal information to the target model and design the imperceptible-high attack success rate constraint to guide the Gabor filter to select appropriate angles and scales to smooth the linear texture from the input images to generate adversarial examples. Benefiting from the above design concept, AdvSmo will generate adversarial examples with strong transferability and solid evasiveness. Finally, compared to the four advanced black-box adversarial attack methods, for the eight target models, the results show that AdvSmo improves the average attack success rate by 9% on the CIFAR-10 and 16% on the Tiny-ImageNet dataset compared to the best of these attack methods.

Hui Xia, Rui Zhang, Zi Kang et al.

Most black-box adversarial attack schemes for object detectors mainly face two shortcomings: requiring access to the target model and generating inefficient adversarial examples (failing to make objects disappear in large numbers). To overcome these shortcomings, we propose a black-box adversarial attack scheme based on semantic segmentation and model inversion (SSMI). We first locate the position of the target object using semantic segmentation techniques. Next, we design a neighborhood background pixel replacement to replace the target region pixels with background pixels to ensure that the pixel modifications are not easily detected by human vision. Finally, we reconstruct a machine-recognizable example and use the mask matrix to select pixels in the reconstructed example to modify the benign image to generate an adversarial example. Detailed experimental results show that SSMI can generate efficient adversarial examples to evade human-eye perception and make objects of interest disappear. And more importantly, SSMI outperforms existing same kinds of attacks. The maximum increase in new and disappearing labels is 16%, and the maximum decrease in mAP metrics for object detection is 36%.

Zhuang Qian, Shufei Zhang, Kaizhu Huang et al.

In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial training method through robust optimization, and a tractable way to generate Latent Manifold Adversarial Examples (LMAEs) via an adversarial game between a discriminator and a classifier. The proposed adversarial training with latent distribution (ATLD) method defends against adversarial attacks by crafting LMAEs with the latent manifold in an unsupervised manner. ATLD preserves the local and global information of latent manifold and promises improved robustness against adversarial attacks. To verify the effectiveness of our proposed method, we conduct extensive experiments over different datasets (e.g., CIFAR-10, CIFAR-100, SVHN) with different adversarial attacks (e.g., PGD, CW), and show that our method substantially outperforms the state-of-the-art (e.g., Feature Scattering) in adversarial robustness by a large accuracy margin. The source codes are available at https://github.com/LitterQ/ATLD-pytorch.