Web 3.0, built on blockchain technology, prioritizes user privacy and autonomy, presenting new opportunities for financial systems while also complicating the regulation of illicit activities. In this study, we present a novel infrastructure named Pseudo Fine-tuning (PFT) that provides account matching services to combat financial crimes on account-based blockchains such as money laundering through coin-mixing services. The significance of PFT lies in overcoming the need for real labels to fine-tune language models for account matching, given the limited availability of labeled account pairs for the task. Specifically, our design involves (1) crafting pseudo-labeled pairs from transactions of an account across different periods, and (2) fine-tuning language models to distill knowledge from pseudo pairs, which is transferable to the target task. We provide an in-depth analysis to investigate the inherent knowledge acquired during the PFT process and the conditions conducive to its effectiveness. Comprehensive experiments on real-world datasets collected from coin-mixing services and ENS name services, corroborate that the framework delivers pronounced enhancements over state-of-the-art approaches. Our implementation is released at https://github.com/git-disl/PFT .

Adversarial perturbations are useful tools for exposing vulnerabilities in neural networks. Existing adversarial perturbation methods for object detection are either limited to attacking CNN-based detectors or weak against transformer-based detectors. This paper presents an Attention-Focused Offensive Gradient (AFOG) attack against object detection transformers. By design, AFOG is neural-architecture agnostic and effective for attacking both large transformer-based object detectors and conventional CNN-based detectors with a unified adversarial attention framework. This paper makes three original contributions. First, AFOG utilizes a learnable attention mechanism that focuses perturbations on vulnerable image regions in multi-box detection tasks, increasing performance over non-attention baselines by up to 30.6%. Second, AFOG's attack loss is formulated by integrating two types of feature loss through learnable attention updates with iterative injection of adversarial perturbations. Finally, AFOG is an efficient and stealthy adversarial perturbation method. It probes the weak spots of detection transformers by adding strategically generated and visually imperceptible perturbations which can cause well-trained object detection models to fail. Extensive experiments conducted with twelve large detection transformers on COCO demonstrate the efficacy of AFOG. Our empirical results also show that AFOG outperforms existing attacks on transformer-based and CNN-based object detectors by up to 83% with superior speed and imperceptibility. Code is available at https://github.com/zacharyyahn/AFOG.

This article presents FusionShot, a focal diversity-optimized few-shot ensemble learning approach for boosting the robustness and generalization performance of pre-trained few-shot models. The article makes three original contributions. First, we explore the unique characteristics of few-shot learning to ensemble multiple few-shot (FS) models by creating three alternative fusion channels. Second, we introduce the concept of focal error diversity to learn the most efficient ensemble teaming strategy, rather than assuming that an ensemble of a larger number of base models will outperform those sub-ensembles of smaller size. We develop a focal diversity ensemble pruning method to effectively prune out the candidate ensembles with low ensemble error diversity and recommend top- \( K \) FS ensembles with the highest focal error diversity. Finally, we capture the complex non-linear patterns of ensemble few-shot predictions by designing the learn-to-combine algorithm, which can learn the diverse weight assignments for robust ensemble fusion over different member models. Extensive experiments on representative few-shot benchmarks show that the top-K ensembles recommended by FusionShot can outperform the representative state-of-the-art (SOTA) few-shot models on novel tasks (different distributions and unknown at training) and can prevail over existing few-shot learners in both cross-domain settings and adversarial settings. For reproducibility purposes, FusionShot trained models, results, and code are made available at https://github.com/sftekin/fusionshot .

Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attractive property of diversity optimized ensemble learning is its robustness against deception: an adversarial perturbation attack can mislead one DNN model to misclassify but may not fool other ensemble DNN members consistently. In this paper we first give an overview of the concept of ensemble diversity and examine the three types of ensemble diversity in the context of DNN classifiers. We then describe a set of ensemble diversity measures, a suite of algorithms for creating diversity ensembles and for performing ensemble consensus (voted or learned) for generating high accuracy ensemble output by strategically combining outputs of individual members. This paper concludes with a discussion on a set of open issues in quantifying ensemble diversity for robust deep learning.

While location-based services and applications are increasing in popularity, there are growing concerns over users' location privacy. Although there exist general purpose mobile permission systems and cloaking techniques, these techniques suffer from several problems when applied to continuous location and GPS access, as they are often rigid, coarse-grained, not sufficiently personalizable, and unaware of road network semantics. This paper proposes PrivacyZone, a novel system for constructing personalized fine-grained privacy quarantine regions and protecting users' privacy within these regions. PrivacyZone allows users to seamlessly enter their privacy specifications under spatial, temporal, and semantic customization. Novel challenges arise from having to enforce privacy zones for large volume and variety of users with frequent location updates. We show that naive privacy zone processing techniques are inefficient and cause excessive energy consumption. We therefore develop advanced processing techniques based on the concept of safe hibernation. We empirically evaluate our techniques to demonstrate their trade-offs with respect to hibernation time, computation effort, and network bandwidth usage. Our results show that PrivacyZone is efficient, scalable, and flexible, while preserving users' location privacy.

In the coming decades, we will live in a world surrounded by tens of billions of devices that will interoperate and collaborate in an effort to deliver personalized and autonomic services. This paradigm of smart objects and smart things interconnected and ubiquitously surrounding us is called the Internet of Things (IoT). Cities may be the first to benefit from the IoT, but reliance on these machines to make decisions has profound implications for trust, and makes mechanisms for expressing and reasoning about trust essential. This paper introduces the project funded by the Georgia Tech Research Institute to look at several dimensions of Machine to Machine Trust in the context of Smart Cities.

The ability to execute the original source code for network protocols and applications within a network simulation environment frees the simulation modeler from the time consuming task of having to create, test and debug models representing these applications. This work extends the functionality of the Direct Code Execution (DCE) framework of ns-3 by incorporating the ability to call NVIDIA CUDA kernels from within simulated ns-3 nodes. This new functionality allows researchers to simulate large scale GPU applications in the realm of new and more flexible paradigms such as software-defined networking. Along with presenting this new functionality, this paper examines the different options available within the framework for communicating between the simulated nodes and the GPU. Each implementation is tested with multiple example CUDA kernels to demonstrate how they perform.

There continues to be many advances in the theory and practice of Modeling and Simulation (M&S). However, some of these can be considered as Grand Challenges; issues whose solutions require significant focused effort across a community, sometimes with ground-breaking collaborations with new disciplines. In 2002, the first M&S Grand Challenges Workshop was held in Dagstuhl, Germany, in an attempt to focus efforts on key areas. In 2012, a new initiative was launched to continue these Grand Challenge efforts. Panel members of this third Grand Challenge present their views on M&S Grand Challenges. Themes presented in this panel include M&S Methodology; Agent-based M&S; M&S in Systems Engineering; Cyber Systems Modeling; and Network Simulation.

Approximate Time (AT) has been proposed as a means for expressing temporal uncertainty in distributed simulation applications in order to enhance parallel performance. This is accomplished by specifying time intervals rather than precise values to indicate when an event might occur. This paper describes a case study in applying AT to a queueing simulation application in order to assess the performance and accuracy that can be obtained using this technique. Up to an order of magnitude speedup was obtained, with error in throughput statistics less than 3%, although somewhat larger error was reported in delay statistics.

As the power and potential to create robust distributed interactive simulation (DIS) environments using the technical principles introduced by the SIMNET project gains recognition, the need for establishing standards for the implementation of these principles has grown dramatically. Initially, the interest in achieving interoperability between many disparate simulation components drove the work in developing standards. More recently, an equally important aspect for establishing standards has been to expand the market opportunities for simulation component suppliers. During the past five years, Workshops on Standards for the Interoperability of Distributed Simulations have provided the forum for establishing standards for networking dissimilar simulations to create virtual worlds in which many subjects can interact. These virtual worlds can be used for training individuals, testing equipment, prototyping products, research and development or any application involving the interaction of groups of people in a common synthetic environment.>