5 August 2020 in IEEE Transactions on Geoscience and Remote Sensing
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.
6 April 2022 in International Journal of Computer Vision
29 March 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
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 A dversarial s patial- t emporal 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 time.
13 June 2024 in IEEE Transactions on Intelligent Transportation Systems
The reliability and robustness of 3D object detection play an instrumental role in the practical deployment of autonomous driving systems. Despite previous research indicating that adversarial examples can negatively affect 3D object detection models, leading to misinterpretations of the environment, these models still maintain the capability to detect the majority of objects within adversarially manipulated point clouds. To further probe into the adversarial robustness of these models, we propose an effective adversarial attack method named IoU-S attack in this paper. We meticulously formulate the adversarial loss to adversely affect the decision-making behavior (such as localization, etc.) of 3D object detection, thereby compromising its ability to accurately interpret the environment. Owing to the significant relevance of this adversarial loss to 3D object detection tasks, we have integrated the IoU-S attack into three attack paradigms: point cloud perturbation, detachment, and attachment. Comprehensive experiments on the widely accepted nuScenes dataset illustrate that the IoU-S attack outperforms existing attack methods in both white-box and black-box scenarios (https://github.com/haichen-ber/IoU-S-Attack). It reinforces its potential to serve as a valuable method in understanding and enhancing the robustness of 3D object detection models against adversarial attacks.
2 June 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Ship detection in spaceborne optical images is a challenging task because ships have various orientations and scales, especially complex backgrounds, i.e., ships are easily obscured by various jamming. Moreover, most accurate object detectors have enormous computation and parameter numbers, which are unsuitable for resource-bounded spaceborne platforms that contain restrictive memory access and computation. In this paper, in order to cope with the influence of complex backgrounds and jamming on detection, and improve the practicality of detection algorithms, a new satellite optical image dataset and a novel ship detector are proposed. We have collected a new dataset from the satellite, which contains images of different time periods, different illuminations, and different levels of jamming. The proposed dataset is different from the widely used public remote sensing datasets, it is more practical and challenging. The proposed ship detector can deal with various images well and is robust to various complex backgrounds. Specifically, a feature refining module is designed to extract features effectively, which can improve detection performance significantly. An anti-jamming module is proposed to highlight the features of objects in the whole feature map. In contrast to mainstream ship detectors, the proposed method is effective and lightweight. It can also predict objects with oriented bounding boxes. Extensive experiments demonstrate that the proposed detector is efficient and robust to various complex backgrounds, and the new dataset CBSD is more suitable for application scenarios and is quite challenging.
2 August 2024 in IEEE Transactions on Big Data
Transfer-based adversarial attacks involve generating adversarial point clouds in surrogate models and transferring them to other models to assess 3D model robustness. However, current methods rely too much on surrogate model parameters, limiting transferability. In this work, we use Shapley value to identify positive and negative features, guiding optimization of adversarial noise in feature space. To effectively mislead the 3D classifier, we factorize the adversarial noise into positive and negative noise, with the former keeping the features of the adversarial point cloud close to the negative features, and the latter and the adversarial noise moving it away from the positive features. Finally, a novel adversarial point cloud attack method with Adversarial Noise Factorization is proposed, which is abbreviated as ANF. ANF simultaneously optimizes the adversarial noise and its positive and negative noise in the feature space, only relying on partial network parameters, which significantly reduces the reliance on the surrogate model and improves the transferability of the adversarial point cloud. Experiments on well-recognized benchmark datasets show that the transferability of adversarial point clouds generated by ANF could be improved by more than 26.7$\%$ on average over state-of-the-art transfer-based adversarial attack methods.