Machine learning has made tremendous progress and applied to various critical practical applications. However, recent studies have shown that machine learning models are vulnerable to malicious attackers, such as neural network backdoor triggering. A successful backdoor triggering behavior may cause serious consequences, such as allowing the attacker to bypass the identity verification and directly enter the system. In image classification, there is always only one target label triggered by one backdoor trigger in previous works. The position of the backdoor trigger is also fixed, which brings limitations to the attack. In this paper, we propose a novel method that utilizes one trigger pattern to correspond to multiple target labels, and the location of the trigger is not limited. In our method, the trigger guarantees that the malicious output is within the range of multiple targets chosen by the attacker, but the specific target depends on the original image where the trigger is pasted. Due to the original images' diversity, it is difficult for the defender to predict which target the image with the trigger is classified as. Besides, the attacker can use only one trigger pattern to achieve multitarget attacks at different locations, which brings more flexibility. We also proposed to train a neural network as a detector to distinguish backdoor images and clean images for multitarget backdooring attacks. Experiment results show that the detection method can also successfully detect the backdoor image with a trigger at a random location of the image, and the detection success rate is as high as 86.02%.

There is a rapidly growing interest in securing big data due to the rapid development of cloud computing, big data, and other information technologies according to the fourth industrial revolution. Continuous data protection (CDP) is an effective method to deal with huge loss caused by data loss. More optimal design methods are available and studies on the establishment of the knowledge base for an efficient backup data management in the CDP field. In this paper, a knowledge-based smart file-level CDP scheme is suggested. The user's foundation database and context information are applied to machine learning technology, enabling a large amount of files' log data and context information accumulated continuously to be stored in the knowledge base using B + tree structure. This enables high performance and flexibility in the data protection management system. The result of comparative evaluation with different security risk levels for verifying the validity shows that the suggested method presented a higher performance in write/query operations and storage overhead.

The broad application of artificial intelligence (AI) shows more and more vulnerabilities. Adversaries have more opportunities to attack AI systems. For example, unmanned vehicles may be interfered with by adversaries in path planning, resulting in unmanned vehicles being unable to move according to the planned route, and even serious safety problems. On the other side, the portrait technology can extract highly refined characteristics of different attack strategies, so that unmanned vehicles can defend themselves based on the characteristics of each attack. Existing research lacks intelligent attack research on path planning in the field of unmanned vehicles, and lacks portraits of attack behaviors in this scenario. This paper combines multiagent reinforcement learning technology, time-series segmentation clustering technology, and knowledge graph technology to study the portrait technology of adversary intelligent attack behavior in the field of unmanned vehicle path planning. First, the simulation results of unmanned vehicle path planning are obtained, and the steps of adversary attack behavior are extracted by using Toeplitz inverse covariance-based clustering time-series segmentation cluster technology. Second, the knowledge graph is used to save the attack strategy, so as to form the attack behavior portrait of unmanned vehicle path planning. The test on the Neo4j platform shows that our method is universal, can effectively describe the attack steps for unmanned vehicle path planning, and provides the basis for attack detection to establish the defense system of unmanned vehicles.