As online adversarial tactics escalate, particularly with the utilization of large language models, distinguishing phishing emails from benign ones has become increasingly challenging in terms of appearance and semantics. The use of various techniques, including visual deception and the concealment of malicious attachments, has become more widespread, posing significant challenges to traditional machine learning models that rely on text and semantic features. To address these challenges, this study introduces a Fine-grained Phishing Email Risk Assessment framework (FPERA), which focuses on prevalent attack vectors. By integrating techniques such as deep email header inspection, visual analysis, and threat intelligence, FPERA systematically examines potential risk factors across multiple dimensions and calculates the risk score of emails using a risk weighting matrix. Experimental tests conducted on multiple original datasets and AI-generated datasets have demonstrated that detection targeting attack vectors can more effectively counter phishing tactics like AI-enhanced polishing, email header exploits, and visual deception, while exhibiting consistent stability across different datasets.

The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration of learning-based planning strategies. Among these approaches, Imitation Learning stands out due to its notable training efficiency. However, traditional Imitation Learning methodologies encounter challenges associated with the co-variate shift phenomenon. We propose Validity Learning on Failures, VL(on failure), as a remedy to address this issue. The essence of our method lies in deploying a pre-trained planner across diverse scenarios. Instances where the planner deviates from its immediate objectives, such as maintaining a safe distance from obstacles or adhering to traffic rules, are flagged as failures. The states corresponding to these failures are compiled into a new dataset, termed the failure dataset. Notably, the absence of expert annotations for this data precludes the applicability of standard imitation learning approaches. To facilitate learning from the closed-loop mistakes, we introduce the VL objective which aims to discern valid trajectories within the current environmental context. Experimental evaluations conducted on both reactive CARLA simulation and non-reactive log-replay simulations reveal substantial enhancements in closed-loop metrics such as Score, Progress, and Success Rate, underscoring the effectiveness of the proposed methodology. Further evaluations against the Bench2Drive benchmark demonstrate that VL(on failure) outperforms the state-of-the-art methods by a large margin.

Motion planning is one of the key modules in autonomous driving systems to generate trajectories for self-driving vehicles to follow. A common motion planning approach is to generate trajectories within semantic safe corridors. The trajectories are generated by optimizing parametric curves (e.g. Bezier curves) according to an objective function. To guarantee safety, the curves are required to satisfy the convex hull property, and be contained within the safety corridors. The convex hull property however does not necessary hold for time-dependent corridors, and depends on the shape of corridors. The existing approaches only support simple shape corridors, which is restrictive in real-world, complex scenarios. In this paper, we provide a sufficient condition for general convex, spatio-temporal corridors with theoretical proof of guaranteed convex hull property. The theorem allows for using more complicated shapes to generate spatio-temporal corridors and minimizing the uncovered search space to $O\left(\frac{1}{n^{2}}\right)$ compared to O(1) of trapezoidal corridors, which can improve the optimality of the solution. Simulation results show that using general convex corridors yields less harsh brakes, hence improving the overall smoothness of the resulting trajectories.

Motion Planning is one of the key modules in autonomous driving systems to generate trajectories for self-driving vehicles. Spatio-temporal motion planners are often used to tackle complicated and dynamic driving scenarios. While effective in dealing with temporal changes in the environment, the existing methods are limited to optimizing a particular family of cost functions defined based on decoupled longitudinal and lateral terms. However, the planning objectives can only be explained using coupled terms in some cases, e.g. closeness to the reference path, lateral acceleration, and heading rate. The limitation arises from expressing such objectives as linear and quadratic terms suitable for optimization. This paper proposes an approach with theoretical proofs to approximate the upper bound of a given couple, nonlinear cost term with a set of uncoupled terms, allowing for converting the planning optimization problem into a linear quadratic optimization. The effectiveness of the proposed approach is shown through a series of simulated scenarios. The proposed approach results in smoother and steadier trajectories in the spatial plane.

This paper reports a microelectromechanical systems (MEMS)-based microgripper, integrating two-axis actuators and force sensors, for microscale compression and shear testing of soft materials. The device employs V-beam electrothermal actuators to drive an active gripping arm and compress or shear a microscale sample grasped at the gripping tips, and two triplate differential capacitive sensors to measure the compression and shear forces applied to the sample with nanonewton resolution (compressive force resolution: 7.7 nN, and shear force resolution: 57.5 nN). Using the microgripper, we demonstrate, for the first time, on-chip compression and shear testing of polydimethylsiloxane (PDMS) microstructures prepared at different crosslinking levels. We believe that this device will be useful for accurately characterizing mechanical properties of a variety of microscale soft materials.

Many micromanipulation systems employ sensorless actuators and possess unknown modeling errors, feedback measurement noise, and time delays. Conventional modelbased control schemes ignore some of these characteristics, and thus sacrifice the control performance of the system. This paper presents a new model compensation-prediction scheme for control of micromanipulation systems, which estimates the unknown modeling errors from single noisy feedback measurement and predicts and compensate the system time delay. This approach combines two modeling errors into a single equivalent error through mathematical transformation, and estimates the combined term using a noise-insensitive extended high-gain observer (EHGO). After removing the unknown term, the system is then transformed into a time invariant form, and a Smith predictor is implemented to predict and compensate the time delay. The effectiveness of the proposed compensation-prediction scheme is demonstrated by both numerical simulation and experiments of two typical micromanipulation systems. The results show that this method is able to significantly improve the control performance of a conventional PID controller by simultaneously reducing the settling time and overshoot of the system.

The capability of accurately applying millinewton-level touch stimuli to Drosophila larvae and simultaneously observing their resultant fluorescence responses in mechanosensitive neuron transmission will enable novel studies of mechanotransduction neural circuitry. This paper presents an automated robotic micromanipulation system capable of force-controlled mechanical stimulation and quantitative fluorescence imaging of Drosophila larvae, which significantly improves the force regulation accuracy and operation consistency over conventional manual operations. An elastomeric microdevice is developed for efficient immobilization of an array of larvae for subsequent force-controlled touching. A microelectromechanical systems (MEMS) based force sensor is integrated into the robotic system for closed-loop force control of larva touching at a resolution of 50 μN. Two micromanipulators are coordinately servoed using orchestrated position and force control laws for automatic operations. The system performs simultaneous force-controlled larva touching and fluorescence imaging at a speed of four larvae per minute, with a success rate of 92.5%. This robotic system will greatly facilitate the dissection of mechanotransduction mechanisms of Drosophila larvae at both molecular and cellular levels.

Force sensing and control are of paramount importance in robotic micromanipulation. A contact force regulator capable of accurately applying mechanical stimuli to a live Drosophila larva could greatly facilitate mechanobiology research on Drosophila and may eventually lead to novel discoveries in mechanotransduction of neuron circuitry. In this paper, we present a novel contact force scheme implemented in an automated Drosophila larvae micromanipulation system, featuring a switched fuzzy-PD controller and a noise-insensitive extended high gain observer. The switched fuzzy-PD controller inherits the fast convergence from fuzzy controller and overcomes the drawbacks (overshoot and oscillation) of a conventional fuzzy controller. The observer provides precise estimation to compensate for system modeling errors despite force measurement noise, which overcomes the disadvantage of traditional high gain observer. Force control experiments show that, compared to an conventional PID controller, this new controller-observer scheme has significantly enhanced dynamic performance in terms of rising time, overshoot, and oscillation. The developed robotic system and the force control scheme will be applied to mechanical stimulation and fluorescence imaging of Drosophila larvae for identifying new mechanotransduction mechanisms.

Virtual manufacturing (VM) has been proved in different industrial contexts as an effective technology to ensure competitivity and increase profit margins. This paper presents such a system named MEWS, short for module-based extensible integrated VM system. The system now contains 7 modules and owns good extensibility. One of the most important modules is assembling module. It has significant impact on the performance of the system. The adoption of hierarchical assembly model with discrete patches brings many benefits for the whole system as well as the assembling module itself. And the hybrid assembly sequence planning based on subassembly identification with human-interaction expands the planner's scope of application and enhances its robustness, while restricts human-interaction in hierarchical layers of the assembly model.