Abstract. This paper proposes a two-stage framework to address the inverse diffraction grating problem with limited-aperture data. The first stage introduces a deep learning network for data retrieval, featuring a dual-branch, cross-attention architecture. Motivated by an information-theoretic analysis, this design is tailored to separate and adaptively fuse the diffracted field’s low- and high-frequency components, effectively handling their distinct noise sensitivities. The second stage employs a computationally efficient Newton-type algorithm for shape reconstruction, which avoids the need for a forward solver at each iteration. Numerical experiments show that our framework provides accurate and robust reconstructions.

Simulating fuel sloshing within aircraft tanks during flight is crucial for aircraft safety research. Traditional methods based on Navier-Stokes equations are computationally expensive. In this paper, we treat fluid motion as point cloud transformation and propose the first neural network method specifically designed for simulating fuel sloshing in aircraft. This model is also the first deep learning model capable of stably modeling fluid particle dynamics in such complex scenarios. Our triangle feature fusion design achieves an optimal balance among fluid dynamics modeling, momentum conservation constraints, and global stability control. Additionally, we constructed the Fueltank dataset, the first dataset for aircraft fuel surface sloshing. It comprises 320,000 frames across four typical tank types and covers a wide range of flight maneuvers, including multi-directional rotations. We conducted comprehensive experiments on both our dataset and the take-off scenario of the aircraft. Compared to existing neural network-based fluid simulation algorithms, we significantly enhanced accuracy while maintaining high computational speed. Compared to traditional SPH methods, our speed improved approximately 10 times. Furthermore, compared to traditional fluid simulation software such as Flow3D, our computation speed increased by more than 300 times.

Navigating and understanding complex environments over extended periods of time is a significant challenge for robots. People interacting with the robot may want to ask questions like where something happened, when it occurred, or how long ago it took place, which would require the robot to reason over a long history of their deployment. To address this problem, we introduce a Retrieval-augmented Memory for Embodied Robots, or ReMEmbR, a system designed for long-horizon video question answering for robot navigation. To evaluate ReMEmbR, we introduce the NaVQA dataset where we annotate spatial, temporal, and descriptive questions to long-horizon robot navigation videos. ReMEmbR employs a structured approach involving a memory building and a querying phase, leveraging temporal information, spatial information, and images to efficiently handle continuously growing robot histories. Our experiments demonstrate that ReMEmbR outperforms LLM and VLM baselines, allowing ReMEmbR to achieve effective long-horizon reasoning with low latency. Additionally, we deploy ReMEmbR on a robot and show that our approach can handle diverse queries. The dataset, code, videos, and other material can be found at the following link: https://nvidia-ai-iot.github.io/remembr.

General-purpose navigation in challenging environments remains a significant problem in robotics, with current state-of-the-art approaches facing myriad limitations. Classical approaches struggle with cluttered settings and require extensive tuning, while learning-based methods face difficulties generalizing to out-of-distribution environments. This paper introduces X-Mobility, an end-to-end generalizable navigation model that overcomes existing challenges by leveraging three key ideas. First, X-Mobility employs an auto-regressive world modeling architecture with a latent state space to capture world dynamics. Second, a diverse set of multi-head decoders enables the model to learn a rich state representation that correlates strongly with effective navigation skills. Third, by decoupling world modeling from action policy, our architecture can train effectively on a variety of data sources, both with and without expert policies-off-policy data allows the model to learn world dynamics, while on-policy data with supervisory control enables optimal action policy learning. Through extensive experiments, we demonstrate that X-Mobility not only generalizes effectively but also surpasses current state-of-the-art navigation approaches. Additionally, X-Mobility also achieves zero-shot Sim2Real transferability and shows strong potential for crossembodiment generalization. Project page: https://nvlabs.github.io/X-MOBILITY.

To investigate side-channel vulnerabilities in the microarchitecture of multicore processors and develop effective protection strategies, we analyze the primitives of the transient attack known as Meltdown. Our study reveals that the relative window of the exception handler significantly impacts the attack's effectiveness. Focusing on the Intel Skylake architecture, we conduct a comparative analysis between the memory order buffer (MOB), which regulates the execution order of load and store instructions, and the multi-level cache, which enhances data access efficiency. Our findings indicate that threads sharing resources within the core can exploit load instructions to directly access data stored by other users in the store buffer. Additionally, the data reside in cache, influenced by the Least Recently Used (LRU) policy, is particularly vulnerable to data leakage through side-channel attacks. By leveraging transient data from the store buffer and cache, the relative window of the exception handler can be expanded, we demonstrate that incorporating Meltdown can facilitate a transient attack that successfully retrieves the complete communication key of OpenSSH AES.

Federated learning (FL) has been widely applied in Internet of Things (IoT). However, two security problems hinder the proliferation of FL in practical IoT, i.e., privacy leakage and poisoning attacks. To address these problems, various approaches have been proposed from different perspectives. Nevertheless, there remain two critical challenges: 1) how to establish a unified framework for protecting privacy and defending against poisoning attacks and 2) how to implement such methods in the flexible computing architecture of fog computing. In this article, we propose CROSSBEAM, a comprehensive scheme that provides both defense against poisoning attacks and privacy protection for FL in fog computing. Specifically, we construct frameworks to defend against poisoning attacks under both independent and identically distributed (IID) and non-IID settings. Meanwhile, we establish an actively secure framework to protect users’ privacy, building a bridge between privacy protection and poisoning defense. Our CROSSBEAM allows multiple fog nodes and users to collaboratively achieve the FL training. Besides, it can effectively alleviate the negative impact caused by poisoning attacks, meanwhile, users’ data confidentiality can still be guaranteed, even if multiple active fog nodes collude with each other to infer users’ privacy. Additionally, our scheme is of robustness to participants (fog nodes and users) being off-line during the training process. Moreover, benefited from the superiorities of our hierarchical mechanism and secure framework, our scheme can perform with high efficiency. We present rigorous security proof and extensive performance analysis for our CROSSBEAM.

In this paper we present the first safe system for full control of self-driving vehicles trained from human demonstrations and deployed in challenging, real-world, urban environments. Current industry-standard solutions use rule-based systems for planning. Although they perform reasonably well in common scenarios, the engineering complexity renders this approach incompatible with human-level performance. On the other hand, the performance of machine-learned (ML) planning solutions can be improved by simply adding more exemplar data. However, ML methods cannot offer safety guarantees and sometimes behave unpredictably. To combat this, our approach uses a simple yet effective rule-based fallback layer that performs sanity checks on an ML planner's decisions (e.g. avoiding collision, assuring physical feasibility). This allows us to leverage ML to handle complex situations while still assuring the safety, reducing ML planner-only collisions by 95%. We train our ML planner on 300 hours of expert driving demonstrations using imitation learning and deploy it along with the fallback layer in downtown San Francisco, where it takes complete control of a real vehicle and navigates a wide variety of challenging urban driving scenarios.

The public cloud data integrity auditing technique is used to check the integrity of cloud data through the Third Party Auditor (TPA). In order to make it more practical, we propose a new paradigm called integrity auditing based on the keyword with sensitive information privacy for encrypted cloud data. This paradigm is designed for one of the most common scenario, that is, the user concerns the integrity of a portion of encrypted cloud files that contain his/her interested keywords. In our proposed scheme, the TPA who is only provided with the encrypted keyword, can audit the integrity of all encrypted cloud files that contain the user’s interested keyword. Meanwhile, the TPA cannot deduce the sensitive information about which files contain the keyword and how many files contain this keyword. These salient features are realized by leveraging a newly proposed Relation Authentication Label (RAL). The RAL can not only authenticate the relation that files contain the queried keyword, but also be used to generate the auditing proof without sensitive information exposure. We give concrete security analysis showing that the proposed scheme satisfies correctness, auditing soundness and sensitive information privacy. We also conduct the detailed experiments to show the efficiency of our scheme.

The electromagnetic Trojan attack can break through the physical isolation to attack, and the leaked channel does not use the system network resources, which makes the traditional firewall and other intrusion detection devices unable to effectively prevent. Based on the existing research results, this paper proposes an electromagnetic Trojan detection method based on deep learning, which makes the work of electromagnetic Trojan analysis more intelligent. First, the electromagnetic wave signal is captured using software-defined radio technology, and then the signal is initially filtered in combination with a white list, a demodulated signal, and a rate of change in intensity. Secondly, the signal in the frequency domain is divided into blocks in a time-window mode, and the electromagnetic signals are represented by features such as time, information amount, and energy. Finally, the serialized signal feature vector is further extracted using the LSTM algorithm to identify the electromagnetic Trojan. This experiment uses the electromagnetic Trojan data published by Gurion University to test. And it can effectively defend electromagnetic Trojans, improve the participation of computers in electromagnetic Trojan detection, and reduce the cost of manual testing.

In order to resolve the composite material multi-objective topology optimization in aircraft design, a multi-objective aircraft optimization system based on grid technology, the multi-objective optimization grid (MOOG) is put forward. Using grid middleware, MOOG pooled the distributed computational resource into a high-performance computing platform and built a common genetic algorithm computational model towards multi-objective topology optimization. This system provided uniform resource service and visible user using interface. This thesis discussed in detail the system design and the improved multi-objective genetic algorithm. Finally, the solid experimental results of optimizing one type of high aspect ratio wing show that the MOOG has reduced the computation time and has good parallel acceleration