3D object tracking based on deep neural networks has a wide range of potential applications, such as autonomous driving and robotics. However, deep neural networks are vulnerable to adversarial examples. Traditionally, adversarial examples are generated by applying perturbations to individual samples, which requires exhaustive calculations for each sample and thereby suffers from low efficiency during malicious attacks. Hence, the universal adversarial perturbation has been introduced, which is sample-agnostic. The universal perturbation is able to make classifiers misclassify most samples. In this paper, a topology-aware universal adversarial attack method against 3D object tracking is proposed, which can lead to predictions of a 3D tracker deviating from the ground truth in most scenarios. Specifically, a novel objective function consisting of a confidence loss, direction loss and distance loss generates an atomic perturbation from a tracking template, and aims to fail a tracking task. Subsequently, a series of atomic perturbations are iteratively aggregated to derive the universal adversarial perturbation. Furthermore, in order to address the characteristic of permutation invariance inherent in the point cloud data, the topology information of the tracking template is employed to guide the generation of the universal perturbation, which imposes correspondences between consecutively generated perturbations. The generated universal perturbation is designed to be aware of the topology of the targeted tracking template during its construction and application, thus leading to superior attack performance. Experiments on the KITTI dataset demonstrate that the performance of 3D object tracking can be significantly degraded by the proposed method.

To estimate the effectiveness of combining facial expression recognition and machine learning for better detection of distress. 232 patients with cancer in Sichuan University West China Hospital in Chengdu, China. The Distress Thermometer (DT) and Hospital Anxiety and Depression Scale (HADS) were used as instruments. The HADS included scores for anxiety (HADS-A), depression (HADS-D), and total score (HADS-T). Distressed patients were defined by the DT cutoff score of 4, the HADS-A cutoff score of 8 or 9, the HADS-D cutoff score of 8 or 9, or the HADS-T cutoff score of 14 or 15. The authors applied histogram of oriented gradients to extract facial expression features from face images, and used a support vector machine as the classifier. The facial expression features showed feasible differentiation ability on cases classified by DT and HADS. Facial expression recognition could serve as a supplementary screening tool for improving the accuracy of distress assessment and guide strategies for treatment and nursing.

Backdoor attack to deep neural networks (DNNs) is among the predominant approaches to bring great threats into artificial intelligence. The existing methods to detect backdoor attacks focus on the perspective of distributions in DNNs, however, limited by its ability of generalization across DNN models. In this article, a critical-path-based backdoor detector (CPBD) is proposed, which approaches to detect backdoor attacks via DNN’s interpretability. CPBD is designed to efficiently discover the characteristics of backdoors, which distinguish the critical paths in the attacked DNNs. To deal with the intractably large number of neurons, we propose to simplify the neurons, and the preserved key nodes are integrated into a set of critical paths. Thus, a DNN model can be formulated as a combination of several critical paths. Afterward, the detection of backdoors is performed based on the analysis of critical paths corresponding to different classes. Then, combining all the above steps, the CPBD algorithm is integrated to present the results in a standard and systematic manner. In addition, CPBD is able to locate neurons associated with malicious triggers, the combination of which is named as trigger propagation path. Extensive experiments are conducted, which testify the efficiency of the proposed method on multiple DNNs and different trigger sizes.

Due to the inherent vulnerability of Deep Neural Networks (DNNs), Adversarial Example (AE) attack has become a serious threat to intelligent systems, e.g., the failure cause of an image classification system. Different to existing works, in this paper we are interested in the generation of AEs for DNNs with defensive mechanisms. To make the attack more practical, we exploit a query-based method to generate image AEs in a black-box attack setting. Considering that the generation of AEs is inherently a constrained optimization problem, this paper first formulates three objectives regarding to defensive DNNs, i.e, attack effectiveness, attack evasiveness and attack coverage. Then, this paper proposes a query-efficient AE attack based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to address the perturbation optimization problem. To improve the efficiency of search and query, AE-specific operators including block-level and pixel-level crossovers, discrete perturbation mutation and direction-driven reproduction are designed within the GA-based search framework. In addition, predication-based adaptation of reproduction-related parameters is implemented to speed up the search convergence. PSO-based jumping process is further devised to avoid stuck in local optimum. Benchmark-based experiments evaluated the efficiency of our method, which can achieve an attack success rate of 100% with averagely 52.95% reduced queries in contrast to existing black-box attacks on non-defensive models. For defensive DNN models, our method can obtain top attack performance with the query reduction up to 70.92% comparing with the candidates.