ABCAttack: A Gradient-Free Optimization Black-Box Attack for Fooling Deep Image Classifiers.

The vulnerability of deep neural network (DNN)-based systems makes them susceptible to adversarial perturbation and may cause classification task failure. In this work, we propose an adversarial attack model using the Artificial Bee Colony (ABC) algorithm to generate adversarial samples without the need for a further gradient evaluation and training of the substitute model, which can further improve the chance of task failure caused by adversarial perturbation. In untargeted attacks, the proposed method obtained 100%, 98.6%, and 90.00% success rates on the MNIST, CIFAR-10 and ImageNet datasets, respectively. The experimental results show that the proposed ABCAttack can not only obtain a high attack success rate with fewer queries in the black-box setting, but also break some existing defenses to a large extent, and is not limited by model structure or size, which provides further research directions for deep learning evasion attacks and defenses.

Local spatial obesity analysis and estimation using online social network sensors.

Recently, the online social networks (OSNs) have received considerable attentions as a revolutionary platform to offer users massive social interaction among users that enables users to be more involved in their own healthcare. The OSNs have also promoted increasing interests in the generation of analytical, data models in health informatics. This paper aims at developing an obesity identification, analysis, and estimation model, in which each individual user is regarded as an online social network 'sensor' that can provide valuable health information. The OSN-based obesity analytic model requires each sensor node in an OSN to provide associated features, including dietary habit, physical activity, integral/incidental emotions, and self-consciousness. Based on the detailed measurements on the correlation of obesity and proposed features, the OSN obesity analytic model is able to estimate the obesity rate in certain urban areas and the experimental results demonstrate a high success estimation rate. The measurements and estimation experimental findings created by the proposed obesity analytic model show that the online social networks could be used in analyzing the local spatial obesity problems effectively.

Enhance embedding capacity for switch map based multi-group EMD data hiding.

Exploiting Modification Direction (EMD) based data hiding achieves good stego-image quality and high security level. Recently, a section-wise EMD was proposed to enhance the embedding capacity of EMD. Later, Wang et al. introduced a switch map based multi-group EMD to further improve the embedding capacity. However, by a detail observation on the switch map in Wang et al.'s scheme, we find that more codewords with longer code-length can be put into the switch map. In this paper, we build a new switch map by Huffman code, and construct an enhanced multi-group EMD using Huffman code based switch map. Our scheme has higher embedding capacity than Wang et al.'s scheme and other EMD based data hiding methods.