An automatic, fast, and accurate switching method between Global Positioning System and indoor positioning systems is crucial to achieve current user positioning, which is essential information for a variety of services installed on smart devices, e.g., location-based services (LBS), healthcare monitoring components, and seamless indoor/outdoor navigation and localization (SNAL). In this study, we proposed an approach to accurately detect the indoor/outdoor environment according to six different daily activities of users including walk, skip, jog, stay, climbing stairs up and down. We select a number of features for each activity and then apply ensemble learning methods such as Random Forest, and AdaBoost to classify the environment types. Extensive model evaluations and feature analysis indicate that the system can achieve a high detection rate with good adaptation for environment recognition. Empirical evaluation of the proposed method has been verified on the HASC-2016 public dataset, and results show 99% accuracy to detect environment types. The proposed method relies only on the daily life activities data and does not need any external facilities such as the signal cell tower or Wi-Fi access points. This implies the applicability of the proposed method for the upper layer applications.

Increasing integration of the information communication technology introduces security vulnerabilities into smart grid. False data injection attack can exploit the cyber vulnerabilities to compromise the physical grid without being detected. However, the existing attack strategies only consider the electrical characteristic of power flow calculation to induce multiple overloaded branches. On this basis, our attack strategy absorbs the topological adjacency of chain subgraph to induce the overloaded branch chains, which can better characterize the sequential propagation of cascading failures. To this end, a game-theoretical bilevel optimization problem is formulated to model the decision-making interaction between the upper-level attacker and the lower-level security constrained economic dispatching system. The simulation results in IEEE test systems verify that our attack strategy can induce the overloaded branch chains and justify that the overloaded branch chains are more effective than the overloaded branches in triggering the cascading failures.

Extensive studies have revealed that the prevalent deep neural networks (DNNs) are vulnerable to adversarial examples in image recognition tasks. However, previous adversarial example attacks always work in either the global semantic space or local semantic attributes, resulting that these attacks may violate the sophisticated attackers’ least-effort intentions, whereas adversarial perturbations due to the explicit semantic variations are probably perceived by human vision. In this paper, we propose a two-phase optimization modeling framework to devise a novel Critical Semantic Fusion guided least-effort Adversarial example attack (CSFAdv). Specifically, the first phase fuses the coarse-&fine-grained semantic maps to localize the latent critical semantic attention region (CSAR) from genuine image. Under the friendly guidance of CSAR-feasibility, the second phase absorbs the ReLU-penalization, L ₀ -regularization and L _∞ -limitation to formulate a Top-1&Top-2 misclassification optimization problem, which can characterize the holistic least-effort tampering behaviors embodied in localizing the most critical semantic space, doctoring the least amounts of pixels, injecting the limited amplitudes of perturbations and launching the most readily adversarial attacks. Further, to solve this NP-hard problem mildly, we adapt the gradient renewal by means of merging the momentum (past gradient), present gradient and Hessian (future gradient) to formalize a generalized gradient descent algorithm for generating an optimal adversarial image. Finally, we perform numerical experiments to verify the validity of our CSFAdv against seven types of DNN-based image classifiers on three public ImageNet, MNIST and CIFAR10. Empirical illustrations from ten evaluations indices shed light on the superiority of CSFAdv over eight kinds of state-of-the-art attacks and also offer key clues in reinforcing the DNNs’ robustness.

Extensive investigations have revealed that the gait recognition system is always vulnerable to impersonation attacks, which pose significant threats to the identity access security. Previous impersonation strategies have primarily focused on mimicking the victim’s walking style or probing the similar gait features to merely manipulate the input samples, without concurrently undermining the built-in model of the gait recognizer, thereby failing to achieve cost-effective attacks. In contrast to these existing heuristic approaches, we propose an optimal adversarial complicity strategy, called collusion attack, which leverages the tight collaboration between an external attacker and an internal spy to tie up into the close colluder, simultaneously enabling the input-&model-corrupted tampering modes and misleading the gait recognizer more powerfully and stealthily for misidentifying the illegitimate Alice as legitimate Bob. Specifically, we formulate a bilevel optimization problem to model such a leader-follower Stackelberg game with sequentially adversarial interaction process between the colluders and gait recognizer. Further, to solve this challenging bilevel problem efficiently, we absorb the Lagrangian dual theory and linearization representation method to reformulate a tractable mixed integer program. Finally, we perform comparison and ablation experiments with the state-of-the-art attack modes on single-&multi-source gait datasets to verify the validity of our collusion strategy in inducing the mistaken identity with great success rate, high confidence, and low cost. Empirical results also shed light on key insights in mitigating the collusion attacks and enhancing the gait recognition robustness to safeguard the identity access applications.

Extensive studies have revealed that gait-based identity recognition (GBIR) system is extremely vulnerable to the exogenous imitation attacks, but lacking to investigate their adversarial game behaviors in the most intentional manner so that its endogenous robustness is underestimated severely. In this paper, to evaluate the robustness adequately, we absorb the bilevel optimization framework to generate the worst noisy perturbations and formalize the so-called robustness evaluator. Specifically, the adversarial interaction process between the attacker and gait recognizer are characterized as the classical leader-follower game, in which the recognizer can be fooled to misrecognized an unauthenticated user as specific authenticated victim. Finally, we perform experiments to verify the validity of our proposed robustness evaluator on different-scale datasets. Empirical results not only shed light on the huge potential of our modeling framework toward the vulnerability assessments and robustness evaluation of GBIR, but also offer the core clues in the mitigation tactics with multi-modal data fusion to enhance its robustness.