ConvNet-based object detection networks have achieved outstanding performance on clean images. However, many works have shown that these detectors perform poorly on corrupted images caused by noises, blurs, poor weather conditions and so on. With the development of security-sensitive applications, the detector's practicability has raised increasing concerns. Existing approaches improve detector robustness via extra operations (image restoration or training on extra labeled data) or by applying adversarial training at the expense of performance degradation on clean images. In this paper, we present Selective Adversarial Learning with Constraints (SALC) as a universal detector training approach to simultaneously improve the detector's precision and robustness. We first propose a unified formulation of adversarial samples for multitask adversarial learning, which significantly diversifies the obtained adversarial samples when integrated into the adversarial training of the detector. Next, we examine our findings on model bias against adversarial attacks of different strengths and differences in Batch Normalization (BN) statistics among clean images and different adversarial samples. On this basis, we propose a batch local comparison strategy with two BN branches to balance the detector's accuracy and robustness. Furthermore, to avoid performance degradation caused by overwhelming subtask losses, we leverage task-aware ratio thresholds to control the influence of learning in each subtask. The proposed approach can be applied to various detectors without any extra labeled data, inference time costs, or model parameters. Extensive experiments show that our SALC achieves state-of-the-art results on both clean benchmarks (Pascal VOC and MS-COCO) and corruption benchmarks (Pascal VOC-C and MS-COCO-C).

Aiming at degrading the capability of the existing forensic methods in discriminating computer generated and natural facial images, a bidirectional conversion between computer-generated and natural facial images based on generative adversarial network (BDC-GAN) is proposed for anti-forensics in this paper. The generator of BDC-GAN is composed of noise encoding and content encoding. In the noise encoding, three high-pass filters are first utilized to extract the sensor pattern noise of the image, and then the stacked convolution layer is combined to continue encoding. In the content encoding, VGG-19 is truncated and fine-tuned to encode the content of the image. Some stacked convolution layers and adaptive instance normalization layer are used in the decoder. The discriminator uses multi-scale image discriminator. Furthermore, content loss and noise loss are well designed, and hyperparameters are reasonably set to accomplish the bidirectional conversion between two domain images meanwhile retaining the original facial contour. Experimental results and analysis demonstrate that the proposed anti-forensic method can achieve better visual quality and stronger deception ability compared with the existing unidirectional CG facial image anti-forensic methods and bidirectional domain adaptive methods, and its effectiveness is verified by the tests on the existing 9 forensic methods. It reveals that the existing forensic techniques can be bypassed by using adversarial learning, and it will eventually push the performance improvement of the discrimination of computer generated and natural facial images.

In this article, the optimal operational control problem is considered for complex industrial processes with stochastic disturbances. The performance index is optimized by set points reselection on the operational control layer together with controllers design on the loop control layer. First, the operational indices are obtained through some optimization algorithms. Second, the controllers are designed in the ideal situation to ensure that the controlled variables can track desired set points. To minimize the performance deterioration caused by non-Gaussian stochastic noises or disturbances, a novel Pareto distribution estimation (Pareto DE)-based intelligent set-points reselection approach is proposed to optimize entropy and expectation simultaneously. In the proposed method, entropy is formulated in a recursive way basing on joint PDFs which are obtained through multivariate kernel density and bandwidth selection. Meanwhile, both the controller structure and controller parameters are fixed for whatever disturbances acting on the system. Finally, simulations are given to illustrate the effectiveness of the proposed strategy.

In this paper, a Computer-generated graphics (CG) facial image regeneration scheme for anti-forensics based on generative adversarial network (CGR-GAN) is proposed. The generator of CGR-GAN utilizes a deep U-Net structure, and its discriminator utilizes some stacked convolution layers. Besides, content loss and style loss are both designed to guarantee that the regenerated CG facial images (CGR) retain both the facial profile of the original CG and the characteristics of natural image (NI). Experimental results and analysis demonstrate that the CG facial images regenerated by the proposed anti-forensics scheme can achieve better visual quality compared with those of the existing CG facial image anti-forensics and domain adaptation methods, and it can strike a good balance between visual quality and deception ability.

In this paper, robust minimum entropy tracking control problem is considered for nonlinear stochastic systems. The controlled systems are described by nonlinear non-Gaussian difference equations with the un-modeled uncertainty and modeling error, as well as time delays. Entropy is adopted to characterize the uncertainty of the tracking error. The nonlinear multi-step-ahead predictive cost function is used and the relationship between the probability density functions of the input and the tracking error via the uncertain mapping is established. With these formulations, the cost function can be bounded as a nonlinear functional of the control input and the known bounds of the errors. Explicit design algorithms are presented for the robust suboptimal controller and further for the stabilization controllers. The Renyi's entropy has also been used to simplify the cost function. Simulations are given to demonstrate the effectiveness of the proposed control algorithm.