Narrow Results

This paper proposes a Finite State Machine (FSM) testing technique based on deep neural network (DNN). This technique verifies the correctness of an implementation FSM-B of a specification FSM-A. Using the back-propagation algorithm, a deep neural network is trained with the input–output patterns for a given set of transition functions that specify an FSM. Initially, for FSM-A, the input patterns and the corresponding output patterns (I/O pairs) are generated. Then most of the patterns are used to train the DNN. Once the training is over, the DNN is validated with the remaining I/O pairs (around 20%). The model can be used for verifying the correctness of FSM-B after training and validation of the DNN. Some inputs are applied to FSM-B and the generated output patterns are compared with the predicted values of the proposed DNN. The difference of accuracy percentages between FSM-A and FSM-B is recorded and zero difference between them indicates the fault-free condition of the implementation FSM-B. To check the effectiveness of the scheme, the output- and state-type faults are injected to derive mutant FSMs. Experimental results performed on the MCNC FSM benchmarks prove the efficacy of the proposed method. Only a few numbers of tests are needed to detect the presence of anomaly, if any. Hence, the test time reduces significantly — resulting in an average test time reduction of 85.67% compared to the conventional techniques. To the best of our knowledge, for the first time a DNN-driven testing scheme is being proposed.

This work proposes a $d$-dimensional quantum multi-secret sharing scheme with a cheat-detection mechanism. The dealer creates multiple secrets and distributes the shares of these secrets using multi-access structures and a monotone span program. The dealer detects the cheating of each participant using the black box’s cheat-detection mechanism. To detect the participants’ deceit, the dealer distributes secret shares’ shadows derived from a randomly invertible matrix $X$ to the participants, stored in the black box. The black box identifies the participant’s deceitful behavior during the secret recovery phase. Only honest participants authenticated by the black box acquire their secret shares to recover the multiple secrets. After the black box cheating verification, the participants reconstruct the secrets by utilizing the unitary operations and quantum Fourier transform. The proposed protocol is reliable in preventing attacks from eavesdroppers and participants. The scheme’s efficiency is demonstrated in different noise environments: dit-flip noise, $d$-phase-flip noise and amplitude-damping noise, indicating its robustness in practical scenarios. The proposed protocol provides greater versatility, security and practicality.

Most current vehicle black boxes provide a bird’s-eye view of 2D type. This viewpoint has a limited viewing angle which makes it difficult to conduct an accident investigation, parking and awareness of space. To solve these problems, we propose the 3D Around View Monitoring (AVM) algorithm using image composition which combines planar and hemispherical projection method. The experimental results indicate that the proposed method overcome the 2D AVM disadvantages and may be useful for accurate accident investigation, autonomous driving system and other system.

Explainability and comprehensibility of AI are important requirements for intelligent systems deployed in real-world domains. Users want and frequently need to understand how decisions impacting them are made. Similarly, it is important to understand how an intelligent system functions for safety and security reasons. In this paper, we describe two complementary impossibility results (Unexplainability and Incomprehensibility), essentially showing that advanced AIs would not be able to accurately explain some of their decisions and for the decisions they could explain people would not understand some of those explanations.

Black boxes from aircraft which had crashed into the sea are highly difficult to locate. To solve this problem, an identification and location method based on piezoelectric impedance technology was presented in this paper. An experimental device for detecting aircraft black boxes based on impedance analysis was first designed, after which the beacon simulation emitter and piezoelectric impedance acceptor were produced. An experimental platform for detecting and simulating black boxes' ultrasound beacon was set up. For the underwater detection experiment, the signal frequency sent from the simulation generator was set to 37.5kHz, which is the frequency of the ultrasound beacon of the underwater generator on the black box. Combined with the use of back-propagation (BP) neural networks, the ultrasonic beacon was recognized and located. The results show that the largest wave crest always appeared at the frequency of 37.5kHz, and the piezoelectric impedance acceptor's impedance real value curve generally increased as the acceptor got closer to the beacon simulation emitter. This proved that using piezoelectric impedance technology to detect ultrasonic signals sent from the beacon simulation emitter is viable.