Search

Adversarial examples are artificially crafted to mislead deep learning systems into making wrong decisions. In the research of attack algorithms against multi-class image classifiers, an improved strategy of applying category explanation to the generation control of targeted adversarial example is proposed to reduce the perturbation noise and improve the adversarial robustness. On the basis of C&W adversarial attack algorithm, the method uses Grad-Cam, a category visualization explanation algorithm of CNN, to dynamically obtain the salient regions according to the signal features of source and target categories during the iterative generation process. The adversarial example of non-global perturbation is finally achieved by gradually shielding the non-salient regions and fine-tuning the perturbation signals. Compared with other similar algorithms under the same conditions, the method enhances the effects of the original image category signal on the perturbation position. And it makes up for the shortcomings of the adversarial example algorithm in terms of interpretability and teaching intuitiveness. Experimental results show that the improved adversarial examples have higher PSNR. In addition, in a variety of different defense processing tests, the examples can keep high adversarial performance and show strong attacking robustness. [ABSTRACT FROM AUTHOR]

Adversarial examples have begun to receive widespread attention owning to their potential destructions to the most popular DNNs. They are crafted from original images by embedding well-calculated perturbations. In some cases, the perturbations are so slight that neither human eyes nor detection algorithms can notice them, and this imperceptibility makes them more covert and dangerous. For the sake of investigating the invisible dangers in the applications of traffic DNNs, we focus on imperceptible adversarial attacks on different traffic vision tasks, including traffic sign classification, lane detection and street scene recognition. We propose a universal logits map-based attack architecture against image semantic segmentation and design two targeted attack approaches on it. All the attack algorithms generate the micro-noise adversarial examples by the iterative method of C&W optimization and achieve 100% attack rate with very low distortion, among which, our experimental results indicate that the MAE (mean absolute error) of perturbation noise based on traffic sign classifier attack is as low as 0.562, and the other two algorithms based on semantic segmentation are only 1.503 and 1.574. We believe that our research on imperceptible adversarial attacks has a certain reference value to the security of DNNs applications. [ABSTRACT FROM AUTHOR]

By incorporating the interface energy effect into a classical micromechanics framework, effective elastic moduli of a composite material containing randomly distributed nanosized prolate spheroidal inhomogeneities are investigated in this paper. The effect of interface energy, which is usually neglected in classical micromechanics theories, becomes important when the size of the reinforcement phase in the composite enters the nanometer range. The interface energy effect is simulated by inducing interface stress on the zero-thickness membrane interface between the matrix and the inhomogeneities. The interfacial stress discontinuity equations are formulated in accordance with the equilibrium conditions on the idealized interface, from which the interfacial strain discontinuity is solved. Subsequently, the effective elastic moduli are derived based on the classical micromechanics homogenization approaches. Comparisons are made of the effective moduli under the current nanomechanical framework and under classical micromechanical theory. The effective moduli are shown to be dependent upon the size of the inhomogeneities and the interface properties when the interface energy effect is considered. [ABSTRACT FROM AUTHOR]