Search for: All records

Vehicle-to-Everything (V2X) communication enables vehicles to communicate with other vehicles and roadside infrastructure, enhancing traffic management and improving road safety. However, the open and decentralized nature of V2X networks exposes them to various security threats, especially misbehaviors, necessitating a robust Misbehavior Detection System (MBDS). While Machine Learning (ML) has proved effective in different anomaly detection applications, the existing ML-based MBDSs have shown limitations in generalizing due to the dynamic nature of V2X and insufficient and imbalanced training data. Moreover, they are known to be vulnerable to adversarial ML attacks. On the other hand, Generative Adversarial Networks (GAN) possess the potential to mitigate the aforementioned issues and improve detection performance by synthesizing unseen samples of minority classes and utilizing them during their model training. Therefore, we propose the first application of GAN to design an MBDS that detects any misbehavior and ensures robustness against adversarial perturbation. In this article, we present several key contributions. First, we propose an advanced threat model for stealthy V2X misbehavior where the attacker can transmit malicious data and mask it using adversarial attacks to avoid detection by ML-based MBDS. We formulate two categories of adversarial attacks against the anomaly-based MBDS. Later, in the pursuit of a generalized and robust GAN-based MBDS, we train and evaluate a diverse set of Wasserstein GAN (WGAN) models and presentVehicularGAN(VehiGAN), an ensemble of multiple top-performing WGANs, which transcends the limitations of individual models and improves detection performance. We present a physics-guided data preprocessing technique that generates effective features for ML-based MBDS. In the evaluation, we leverage the state-of-the-art V2X attack simulation tool VASP to create a comprehensive dataset of V2X messages with diverse misbehaviors. Evaluation results show that in 20 out of 35 misbehaviors,VehiGANoutperforms the baseline and exhibits comparable detection performance in other scenarios. Particularly,VehiGANexcels in detecting advanced misbehaviors that manipulate multiple fields in V2X messages simultaneously, replicating unique maneuvers. Moreover,VehiGANprovides approximately 92% improvement in false positive rate under powerful adaptive adversarial attacks, and possesses intrinsic robustness against other adversarial attacks that target the false negative rate. Finally, we make the data and code available for reproducibility and future benchmarking, available athttps://github.com/shahriar0651/VehiGAN. 

The vast and rapidly growing amount of science education research makes it challenging for researchers to navigate and synthesize developments across the field, particularly concerning broad concepts evolving along divergent paths. To address this issue, a novel review methodology employing bibliometrics and network analysis was tested to identify and characterize clusters of research focused on the relationship between school‐based science learning and contexts where that science is applied, experienced, observable, or otherwise relevant (e.g., socio‐scientific inquiry, place‐based learning, culturally‐responsive pedagogy). Using a sample of 935 academic papers, the bibliometric network analysis revealed the landscape of contextualized science learning research, identifying 13 distinct clusters of scholarship. Bibliometric and qualitative data were used to describe the research trends within clusters and confirm they were conceptually meaningful and distinct. This methodology facilitated greater understanding of how research can become clustered into “invisible colleges” over time, offering a synthesis approach to grasp interrelated lines of research within an evolving landscape. The methodology has potential to identify other schools of thought or overarching themes in science education, enhancing researchers’ ability to perceive the field as a coherent landscape of interconnected ideas or to identify specific research trajectories within a broad concept. 

Abstract To save saltmarshes and their valuable ecosystem services from sea level rise, it is crucial to understand their natural ability to gain elevation by sediment accretion. In that context, a widely accepted paradigm is that dense vegetation favors sediment accretion and hence saltmarsh resilience to sea level rise. Here, however, we reveal how dense vegetation can inhibit sediment accretion on saltmarsh platforms. Using a process‐based modeling approach to simulate biogeomorphic development of typical saltmarsh landscapes, we identify two key mechanisms by which vegetation hinders sediment transport from tidal channels toward saltmarsh interiors. First, vegetation concentrates tidal flow and sediment transport inside channels, reducing sediment supply to platforms. Second, vegetation enhances sediment deposition near channels, limiting sediment availability for platform interiors. Our findings suggest that the resilience of saltmarshes to sea level rise may be more limited than previously thought. 

In the May issue of Chem Catalysis, Mathison et al. discuss a strategy that leverages biocatalysis and electrocatalysis to decarbonize the production of adiponitrile, a building block of nylon 6,6. High-throughput combinatorial electrosynthesis and machine learning expedited the exploration of the parameter space and the identification of optimal reaction conditions. 

ABSTRACT We present an earthquake simulator, Quake-DFN, which allows simulating sequences of earthquakes in a 3D discrete fault network governed by rate and state friction. The simulator is quasi-dynamic, with inertial effects being approximated by radiation damping and a lumped mass. The lumped mass term allows for accounting for inertial overshoot and, in addition, makes the computation more effective. Quake-DFN is compared against three publicly available simulation results: (1) the rupture of a planar fault with uniform prestress (SEAS BP5-QD), (2) the propagation of a rupture across a stepover separating two parallel planar faults (RSQSim and FaultMod), and (3) a branch fault system with a secondary fault splaying from a main fault (FaultMod). Examples of injection-induced earthquake simulations are shown for three different fault geometries: (1) a planar fault with a wide range of initial stresses, (2) a branching fault system with varying fault angles and principal stress orientations, and (3) a fault network similar to the one that was activated during the 2011 Prague, Oklahoma, earthquake sequence. The simulations produce realistic earthquake sequences. The time and magnitude of the induced earthquakes observed in these simulations depend on the difference between the initial friction and the residual friction μi−μf, the value of which quantifies the potential for runaway ruptures (ruptures that can extend beyond the zone of stress perturbation due to the injection). The discrete fault simulations show that our simulator correctly accounts for the effect of fault geometry and regional stress tensor orientation and shape. These examples show that Quake-DFN can be used to simulate earthquake sequences and, most importantly, magnitudes, possibly induced or triggered by a fluid injection near a known fault system. 

We report the tethering of flame-retardant additives like 9,10-dihydro-9-oxa-10-phosphaphenanthrene-10-oxide (DOPO) to the backbone of a polyamide throughtrans-3-hexenedioic acid, a bioadvantaged derivative of muconic acid.