The widespread use of generative AI has intensified issues related to digital ownership, even as it enhances the efficiency of digital content creation. While watermarking is a primary method for protecting these rights, existing neural network-based approaches often prioritize robustness and imperceptibility, neglecting verifiable ownership. To address this limitation, this paper proposes ChainMark, a system that integrates an invertible neural network (INN) with blockchain technology. ChainMark employs an INN trained within the discrete wavelet transform domain to embed watermarks that are resilient to diverse signal processing attacks. Crucially, unlike traditional approaches that rely solely on watermark extraction, the proposed system secures the verification process through a blockchain smart contract. Experimental results validate the system’s theoretical security and demonstrate that the joint LH-HL model configuration achieves an optimal trade-off between visual quality and extraction accuracy. Consequently, ChainMark effectively guarantees creator rights by ensuring both high-performance watermarking and trustworthy ownership verification.

This study focuses on the robotic capability of ungrasping, or releasing, an object in a grasp from the gripper to the robot's environment. The presented technique enables the delicate release of a grasped object using non-static contacts, allowing for rolling and/or sliding. This dexterous manipulation capability is particularly relevant when ungrasping thin or slender objects, as will be demonstrated with real examples. We initially discuss the establishment of three-dimensional stability during ungrasping manipulation, ensuring robustness. Subsequently, we present a planning and control solution for three-dimensional ungrasping, building upon our previous planar version. A series of experiments across various test scenarios, ranging from precision placement to puzzle tiling, showcase the viability and effectiveness of our approach.

As organizations increasingly seek to build Foundation Models (FMs) using their own proprietary data, many are adopting private and in-house cloud infrastructures (often in addition to public clouds) to address concerns over cost, data privacy, and data sovereignty. However, these isolated private clouds frequently lack interoperability, creating barriers to cross-institutional collaboration, which is vital for training robust Domain-Specific Foundation Models (DSFMs) that rely on large and diverse datasets. Additionally, underutilized resources in private clouds lead to significant global energy inefficiencies. In this paper, we propose the Federated Large Domain Model System (FLDMS), a conceptual framework designed to facilitate collaborative foundation model development across multiple private cloud environments. We review the necessary enabling technologies, including decentralized protocols for data privacy and Large Language Models (LLMs) for automated orchestration, and present a high-level system design demonstrating how these components can be integrated. By enabling secure and efficient cross-organization cooperation, FLDMS provides a blueprint for building DSFMs while addressing the inefficiencies inherent in siloed private cloud systems.

The rise of self-sovereign identity (SSI) technology plays a critical role in addressing the limitations of conventional digital identity management systems. This paper focuses on the credential layer within the SSI technology stack, presenting a comprehensive solution to challenges related to usability, inefficient encryption and decryption processes, and verifiable credential management in existing SSI frameworks. To tackle these issues, the proposed approach introduces a user-friendly private key generation method, a rule table-based encryption and decryption technique, and a verifiable credential management system using smart contracts. In a usability evaluation involving 58 participants, 74.1% rated the proposed approach as user-friendly. Performance evaluations demonstrated that the rule table-based encryption method is between 10.37 and 171.51 times faster than existing encryption techniques. Similarly, the decryption process showed significant improvements, achieving performance that is 16.94 to 58.68 times faster than traditional methods. Security analyses were also conducted, highlighting the resilience against brute-force attacks and unauthorized access. The impact of this research extends beyond addressing current limitations, offering a robust and efficient framework that enhances the usability, security, and performance of SSI systems. By advancing the credential layer, this work paves the way for broader adoption of SSI technology across diverse applications, contributing to the evolution of decentralized identity management solutions. • A decentralized identity management system for Web 3.0 is proposed. • A method for enhancing user autonomy in Web 3.0 is proposed. • A decentralized trust network-based DIM for Web 3.0 is proposed.

The evolution of the metaverse necessitates inventive solutions that can uphold data security. In this paper, we present a novel approach that seamlessly integrates blockchain and substitution cipher techniques to enhance the security landscape of the metaverse. The proposed approach encompasses the generation of the rule table for substitution encryption and decryption, as well as a methodology for data encryption and decryption utilizing the rule table. Furthermore, we conducted a comprehensive evaluation of the proposed approach’s security robustness, especially focusing on its resistance against potential security attacks, including the brute-force attack. Moreover, a series of performance experiments were meticulously conducted to comprehensively gauge the effectiveness and efficiency of the proposed technique. The findings revealed that the proposed approach outperforms asymmetric key algorithms in terms of encryption elapsed time. Additionally, the decryption process of the proposed approach is notably faster than both symmetric and asymmetric key algorithms. The results of security analysis and performance evaluations underscore the viability and efficiency of the proposed approach, positioning it as a promising solution for secure and swift data management within the metaverse environment.

This paper introduces a user authentication technique that utilizes a dynamic SoulBound Token (SBT) to tackle challenges associated with the oracle problem in decentralized environments. The approach uses dual smart contracts – local and global – along with blockchain tokens, removing the need for intermediary verification processes. The proposed method improves security by allowing users direct control over their authentication data, thus mitigating risks associated with centralized authorities and man-in-the-middle attacks. The feasibility and efficacy of this approach are demonstrated through a location-based prototype, indicating significant potential for application in Web 3.0 ecosystems. This paper also provides a comprehensive security analysis, underscoring the robustness of the proposed system against cyber threats.

This study explores the application of a Graph Attention Networks version 2 (GATv2) model in analyzing the Ethereum blockchain network, addressing the challenge posed by its inherent anonymity. We constructed a heterogeneous graph representation of the network to categorize contract accounts (CAs) into different decentralized application (DApp) categories, such as DeFi, gaming, and NFT markets, using transaction history data. Additionally, we developed a link prediction model to forecast transactions between externally owned accounts (EOAs) and CAs. Our results demonstrated the effectiveness of the heterogeneous graph model in improving node embedding expressiveness and enhancing transaction prediction accuracy. The study offers practical tools for analyzing DApp flows within the Web3 ecosystem, facilitating the automatic prediction of CA service categories and identifying active DApp usage. While currently focused on the Ethereum network, future research could expand to include layer 2 networks like Arbitrum One, Optimism, and Polygon, thereby broadening the scope of analysis in the evolving blockchain landscape.

This paper presents an innovative Web 3.0 authentication technique, designed for a user-centric internet environment. Addressing the rising demand for authentication techniques suitable for Web 3.0, it defines the essential features of such systems and introduces a new approach using smart contracts. This approach utilizes mother and child tokens in conjunction with the lock smart contract to ensure secure authentication. The approach is thoroughly tested against various security threats, including man-in-the-middle, replay, and brute-force attacks, and its practicality is evaluated on Ethereum-based networks.

Federated Learning is a machine learning methodology that emphasizes data privacy, involving minimal interaction with each other’s systems, primarily exchanging model parameters. However, this approach can introduce challenges in system development and operation because it inherently faces statistical and system heterogeneity issues. The diverse data storage formats and system environments across clients limit the feasibility of training with a uniform code. To distribute a new code to each environment, active participation of Federated Learning collaborators is necessary, incurring time and cost. Moreover, it impedes adopting modern automated development and deployment paradigms such as DevOps or MLOps. This study investigates how Large Language Models (LLMs) can automatically tailor a single code to individual client environments in heterogeneous scenarios without human intervention. Moreover, to enable the automatic adaptation of the deployed code for conducting new experiments within the system, it is imperative to assess the presence of potentially malicious code that could jeopardize data security. To address this challenge, we introduce a novel prompt engineering technique to enhance LLMs’ detection capabilities, thereby bolstering our ability to detect malicious code effectively.

This study presents the technique of robotic high-speed scooping: rapidly picking an object lying on a support surface by making contact with the object's open top face and the bottom face that is hidden in contact with the support surface. Essential to high-speed scooping is thus to make suitable dynamic, impactful interaction happen among the robot, object, and environment under errors and uncertainties. We propose a solution to this challenge based on stiffness control, an approach for indirect force control using the robot that is arranged to behave like a desired mechanical system. An implementation of the solution is then presented using a custom-built two-fingered direct-drive gripper. Our experiments verify that high-speed scooping operation is achievable, with the duration of dynamic interaction less than 0.3 s, and effective to various scooping situations featuring objects durable and fragile.

When moving objects that are too bulky or heavy to be grasped or lifted, robotic manipulation can benefit from the object's interaction with the support surface and its natural dynamics under gravity. In this work, we show that such dynamic, underactuated manipulation capability can be acquired through reinforcement learning and deployed on real robot systems. First, we present a framework to learn a control policy for object transport in a dynamic simulation environment, featuring the object and the support surface. We then demonstrate successful object locomotion with the learned policy through a set of simulated and real-world experiments, performed with a robot arm and an aerial robot interacting with the object in a non-prehensile manner. While the object, which is in contact with the support surface, oscillates sideways passively under gravity, the robot uses the learned policy to move the object forward with a steady gait by regulating the mechanical energy and the posture of the object. Our experiment results show that the learned policy can transport the object through unmodeled effects of terrain and perturbation.

We present a data-driven approach for effective bin picking from clutter. Recent bin picking solutions usually lead to a direct pinch grasp on a target object without addressing any other potential contact interaction in clutter. However, appropriate physical interaction can be essential to successful singulation and subsequent secure picking, the goal of bin picking. In this work, we contribute a framework that learns physically interactive actions for object picking end-to-end from a visual input in a self-supervised manner. The learned actions enable the robot to purposefully interact with a target object by performing a digging operation through the clutter. By leveraging a fully convolutional network (FCN), we predict picking success probabilities for a set of interactive action primitives that will in turn specify an optimal action to perform. The FCN is trained in a simulated environment through trial and error. Moreover, new datasets are collected using the latest network through iterative self-supervision. Extensive real-world bin picking experiments show the effectiveness and generalizability of the approach.

Bin picking is a challenging problem in robotics due to high dimensional action space, partially visible objects, and contact-rich environments. State-of-the-art methods for bin picking are often simplified as planar manipulation, or learn policy based on human demonstration and motion primitives. The designs have escalated in complexity while still failing to reach the generality and robustness of human picking ability. Here, we present an end-to-end reinforcement learning (RL) framework to produce an adaptable and robust policy for picking objects in diverse real-world environments, including but not limited to tilted bins and corner objects. We present a novel solution to incorporate object interaction in policy learning. The object interaction is represented by the poses of objects. The policy learning is based on two neural networks with asymmetric state inputs. One acts on the object interaction information, while the other acts on the depth observation and proprioceptive signals of robots. The results of experiment shows remarkable zero-shot generalization from simulation to the real world and extensive real-world experiments show the effectiveness of the approach.

This study presents the method of roboticrock-and-walkmanipulation for dynamic, nonprehensile object locomotion. The object, which is in contact with an environmental surface, is basically manipulated to rock from side to side about the contact point periodically by the robot system. In the meantime, the passive dynamics due to gravity enables the object to roll along a zigzag path that leads to a forward walk. Rock-and-walk is a special-purpose method that enables the transport of a certain class of objects, which are too large, heavy to apply other primary methods such as grasping- or pushing-based operations. Our work is motivated by an interesting question in archaeology, how the giant statues of Easter Island (known as “moai”) were transported several hundred years ago, and a recent demonstration performed by archaeologists that it is possible to walk the statue by periodic rocking. We present a detailed study of the dynamics, kinematics, and mechanics of the object-robot-environment system, and devise a feedback control strategy for rock-and-walk gaiting through the effective regulation of the object’s energy and posture. An extensive set of experiments demonstrate the viability and practicality of our approach in diverse settings: Caging-based single-robot manipulation and cable-driven dual-robot manipulation using manipulator arms and aerial robots.

This paper introduces the technique of tilt-and-pivot manipulation, a new method for picking thin, rigid objects lying on a flat surface through robotic dexterous in-hand manipulation. During the manipulation process, the gripper is controlled to reorient about the contact with the object such that its finger can get in the space between the object and the supporting surface, which is formed by tilting up the object, with no relative sliding motion at the contact. As a result, a pinch grasp can be obtained on the faces of the thin object with ease. We discuss issues regarding the kinematics and planning of tilt-and-pivot, effector shape design, and the overall practicality of the manipulation technique, which is general enough to be applicable to any rigid convex polygonal objects. We also present a set of experiments in a range of bin picking scenarios.

This paper presents a novel robotic manipulation technique for transporting objects on the ground in a passive dynamic, nonprehensile manner. The object is manipulated to rock from side to side repeatedly; in the meantime, the force of gravity enables the object to roll along a zigzag path that is eventually heading forward. We call it rock-and-walk object locomotion. First, we examine the kinematics and dynamics of the rocking motion to understand how the states of the object evolve. We then discuss how to control the robot to connect individual rocking motions into a stable gait of the object. Our rock-and-walk object transportation technique is implemented using a conventional manipulator arm and a simple end-effector, interacting with the object in a nonprehensile manner in favor of the passive dynamics of the object. A set of experiments demonstrates successful object locomotion.

This paper presents the technique of flex-and-flip manipulation. It is suitable for grasping thin, flexible linear objects lying on a flat surface. During the manipulation process, the object is first flexed by a robotic gripper whose fingers are placed on top of it, and later the increased internal energy of the object helps the gripper obtain a stable pinch grasp while the object flips into the space between the fingers. The dynamic interaction between the flexible object and the gripper is elaborated by analyzing how energy is exchanged. We also discuss the condition on friction to prevent loss of contact. Our flex-and-flip manipulation technique can be implemented with open-loop control and lends itself to underactuated, compliant finger mechanism. A set of experiments in robotic page turning performed with our customized hardware and software system demonstrates the effectiveness and robustness of the manipulation technique.

This paper addresses assembly sequence planning for constructing planar structures of the common brick wall pattern collectively with mobile modular robots that have the same rectangular footprint. Here we present a new algorithm for target structures with internal holes that our previous algorithm was not able to address. Our new algorithm constructs a feasible assembly sequence where robots do not have to pass through narrow corridors while approaching their target positions. The algorithm is provably correct and complete and runs in time that is linear in the size of a target structure, that is, the number of its parts. We also present software implementing our algorithms and a set of numerical experiments using the software. Finally, we extend our algorithms to address other symmetric patterns formed by a collection of congruent rectangles on the plane.

We present the methodology, algorithms, system design, and experiments addressing the self-assembly of large teams of autonomous robotic boats into floating platforms. Identical self-propelled robotic boats autonomously dock together and form connected structures with controllable variable stiffness. These structures can self-reconfigure into arbitrary shapes limited only by the number of rectangular elements assembled in brick-like patterns. An O(m2) complexity algorithm automatically generates assembly plans which maximize opportunities for parallelism while constructing operator-specified target configurations with m components. The system further features an O(n3) complexity algorithm for the concurrent assignment and planning of trajectories from n free robots to the growing structure. Such peer-to-peer assembly among modular robots compares favorably to a single active element assembling passive components in terms of both construction rate and potential robustness through redundancy. We describe hardware and software techniques to facilitate reliable docking of elements in the presence of estimation and actuation errors, and we consider how these local variable stiffness connections may be used to control the structural properties of the larger assembly. Assembly experiments validate these ideas in a fleet of 0.5 m long modular robotic boats with onboard thrusters, active connectors, and embedded computers.

This paper addresses the self-assembly of a large team of autonomous boats into floating platforms. We describe the design of individual boats, the systems concept, the algorithms, the software architecture and experimental results with prototypes that are 1:12 scale realizations of modified ISO shipping containers, with the goal of demonstrating self-assembly into large maritime structures such as air strips, bridges, harbors or sea bases. Each container is a robotic module capable of holonomic motion that can dock in a brick pattern to form arbitrary shapes. Over 60 modules were built of varying capability. The docking mechanism is designed to be robust to large disturbances that can be expected in the high seas. The docking mechanism also incorporates adjustable stiffness so that the conglomerate can comply to waves representative of sea state three, and have the ability to dynamically stiffen as required. The component modules for autonomous assembly, docking and simultaneous collision-free planning as well as the software architecture are presented along with the description of experimental verification.

We address the problem of synthesizing planar, bimanual, whole-arm grasps by developing the abstraction of an open chain gripper, an open, planar chain of rigid links and revolute joints contacting a planar, polygonal object, and introducing the concept of a generalized contact. Since two generalized contacts suffice for planar grasps, we leverage previous work on caging and immobilization for two contact grasps to construct an algorithm which synthesizes contact configurations for stable grasping. Simulations show that our methodology can be applied to grasp a wide range of planar objects without relying on special-purpose end-effectors. Representative experiments with the PR2 humanoid robot illustrate that this approach is practical.

We address the problem of synthesizing spatial, bimanual, whole-arm grasps by developing the abstractions of an open chain gripper, an open, spatial chain of rigid links and joints between the links, contacting a polyhedral object, and a generalized contact. We show that every general polyhedron can be immobilized by three generalized contacts. We leverage previous work on immobilization to construct an algorithm that synthesizes contact configurations for stable grasping. Our methodology can be applied to grasp a wide range of objects without relying on special-purpose end-effectors as shown in simulations and experiments with a PR2 humanoid robot.