Search

Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when generating adversarial videos. This is especially serious for the query-based black-box attacks where gradient estimation for the threat models is usually utilized, and high dimensions will lead to a large number of queries. To mitigate this issue, we propose to simultaneously eliminate the temporal and spatial redundancy within the video to achieve an effective and efficient gradient estimation on the reduced searching space, and thus query number could decrease. To implement this idea, we design the novel Adversarial spatial-temporal Focus (AstFocus) attack on videos, which performs attacks on the simultaneously focused key frames and key regions from the inter-frames and intra-frames in the video. AstFocus attack is based on the cooperative Multi-Agent Reinforcement Learning (MARL) framework. One agent is responsible for selecting key frames, and another agent is responsible for selecting key regions. These two agents are jointly trained by the common rewards received from the black-box threat models to perform a cooperative prediction. By continuously querying, the reduced searching space composed of key frames and key regions is becoming precise, and the whole query number becomes less than that on the original video. Extensive experiments on four mainstream video recognition models and three widely used action recognition datasets demonstrate that the proposed AstFocus attack outperforms the SOTA methods, which is prevenient in fooling rate, query number, time, and perturbation magnitude at the same., Comment: accepted by TPAMI2023

Depsides are polyphenolic molecules comprising two or more phenolic acid derivatives linked by an ester bond, which is called a depside bond in these molecules. Despite more than a century of intensive research on depsides, the biosynthetic mechanism of depside bond formation remains unclear. In this study, we discovered a polyketide synthase, DrcA, from the fungus

Many studies demonstrate that supervised learning techniques are vulnerable to adversarial examples. However, adversarial threats in unsupervised learning have not drawn sufficient scholarly attention. In this paper, we formally address the unexplored adversarial attacks in the equally important unsupervised clustering field and propose the concept of the adversarial set and adversarial set attack for clustering. To illustrate the basic idea, we design a novel adversarial space-mapping attack algorithm to confuse subspace clustering, one of the mainstream branches of unsupervised clustering. Specifically, it maps a sample into one wrong class by moving it towards the closest point on the linear subspace of the target class, i.e. along the normal of the closest point. The simple single-step algorithm is powerful to craft the adversarial set where the image samples can be wrongly clustered, even into the targeted labels. Empirical results on different image datasets verify the effectiveness and superiority of our algorithm. We further show that deep supervised learning algorithms (such as VGG and ResNet) are also vulnerable to our crafted adversarial set, which illustrates the good cross-task transferability of the adversarial set.

Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either optimizing their perturbation values while fixing the pasting position or manipulating the position while fixing the patch's content. This reveals that the positions and perturbations are both important to the adversarial attack. For that, in this paper, we propose a novel method to simultaneously optimize the position and perturbation for an adversarial patch, and thus obtain a high attack success rate in the black-box setting. Technically, we regard the patch's position, the pre-designed hyper-parameters to determine the patch's perturbations as the variables, and utilize the reinforcement learning framework to simultaneously solve for the optimal solution based on the rewards obtained from the target model with a small number of queries. Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency. Besides, experiments on the commercial FR service and physical environments confirm its practical application value. We also extend our method to the traffic sign recognition task to verify its generalization ability., Accepted by TPAMI 2022

The novel isomerase NsrQ, from Aspergillus novofumigatus, is a key enzyme in the biosynthesis of fungal tetrahydroxanthones and is responsible for dearomatizing cyclization to provide a tetrahydroxanthone scaffold. NsrQ catalyzes a two-step isomerization reaction, involving the isomerization of allylic alcohol and subsequent inversion of configuration at the methyl group. We report on the biochemical and structural characterizations of NsrQ, and its homologue Dcr3, from Diaporthe longicolla. The crystal structures of NsrQ and Dcr3 revealed their similar overall structures, with a cone-shaped α+β barrel fold, to those of the nuclear transport factor 2-like superfamily enzymes. Furthermore, the structures of Dcr3 and NsrQ variants complexed with substrate analogues and the site-directed mutagenesis studies identified the catalytic residues and the important hydrophobic residues in shaping the active site pocket for substrate binding. These enzymes thus utilize Glu and His residues as acid-base catalysts. Based on these observations, we proposed a detailed reaction mechanism for NsrQ-catalyzed isomerization reactions.

Infrared remote-sensing images have irreplaceable value in military and civilian research, such as remote surveillance and military reconnaissance. However, under the conditions of complex scenes, infrared ship detection still faces great challenges. Most importantly, because of the limited hardware resource, the spaceborne satellites usually have weak computational processing ability, which makes the traditional convolution neural network (CNN)-based detection algorithms difficult to show their power. In terms of the above facts, this article proposes a high-performance but low-computation and storage-efficient ship detection algorithm to adapt the severe spaceborne environment. Overall, our method contains the following technical steps: 1) we first present a novel iterative precise segmentation of land and sea algorithm to preprocess the complex and diverse remote-sensing scenes; 2) the multivariate Gaussian distribution is then selected to extract the ship target candidate regions to guarantee the detection recall; 3) we adopt the optical panchromatic data to assist the limited infrared data training; and 4) the cascade decision of multisource features including global and local cues is next utilized to gradually eliminate false alarms. Due to the high efficiency, the proposed method can implement well on the hardware platform of DSP and field-programmable gate array (FPGA) architecture. We conduct a series of experiments and compare with the state-of-the-art object detection algorithms. Experimental results show that our method has fewer parameters but can achieve strong detection robustness against the noise, cloud and reef interfere, which verifies the effectiveness of the proposed method.

Considering the important applications in the military and the civilian domain, ship detection and classification based on optical remote sensing images raise considerable attention in the sea surface remote sensing filed. This article collects the methods of ship detection and classification for practically testing in optical remote sensing images, and provides their corresponding feature extraction strategies and statistical data. Basic feature extraction strategies and algorithms are analyzed associated with their performance and application in ship detection and classification. Furthermore, publicly available datasets that can be applied as the benchmarks to verify the effectiveness and the objectiveness of ship detection and classification methods are summarized in this paper. Based on the analysis, the remaining problems and future development trends are provided for ship detection and classification methods based on optical remote sensing images.

Although there exist various adversarial attacking methods, most of them are performed by generating adversarial noises. Inspired by the fact that people usually set different camera parameters to obtain diverse visual styles when taking a picture, we propose the adversarial attributes, which generate adversarial examples by manipulating the image attributes like brightness, contrast, sharpness, chroma to simulate the imaging process. This task is accomplished under the black-box setting, where only the predicted probabilities are known. We formulate this process into an optimization problem. After efficiently solving this problem, the optimal adversarial attributes are obtained with limited queries. To guarantee the realistic effect of adversarial examples, we bound the attribute changes using L p norm versus different p values. Besides, we also give a formal explanation for the adversarial attributes based on the linear nature of Deep Neural Networks (DNNs). Extensive experiments are conducted on two public datasets, including CIFAR-10 and ImageNet with respective to four representative DNNs like VGG16, AlexNet, Inception v3 and Resnet50. The results show that at most 97.79 % of images in CIFAR-10 test dataset and 98.01 % of the ImageNet images can be successfully perturbed to at least one wrong class with only ⩽ 300 queries per image on average.

In nature, organic molecules with great structural diversity and complexity are synthesized by utilizing a relatively small number of starting materials. A synthetic strategy adopted by nature is pathway branching, in which a common biosynthetic intermediate is transformed into different end products. A natural product can also be synthesized by the fusion of two or more precursors generated from separate metabolic pathways. This review article summarizes several representative branching and converging pathways in fungal natural product biosynthesis to illuminate how fungi are capable of synthesizing a diverse array of natural products.