The protection of cyber Intellectual Property (IP) such as web content is an increasingly critical concern.The rise of large language models (LLMs) with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators.As users increasingly rely on LLM-generated responses, they gradually diminish direct engagement with original information sources, which will significantly reduce the incentives for IP creators to contribute, and lead to a saturating cyberspace with more AIgenerated content.In response, we propose a novel defense framework that empowers web content creators to safeguard their web-based IP from unauthorized LLM real-time extraction and redistribution by leveraging the semantic understanding capability of LLMs themselves.Our method follows principled motivations and effectively addresses an intractable black-box optimization problem.Real-world experiments demonstrated that our methods improve defense success rates from 2.5% to 88.6% on different LLMs, outperforming traditional defenses such as configuration-based restrictions.

Deep Learning has facilitated various high-stakes applications such as crime detection, urban planning, drug discovery, and healthcare. Its continuous success hinges on learning from massive data in miscellaneous sources, ranging from data with independent distributions to graph-structured data capturing intricate inter-sample relationships. Scaling up the data access requires global collaboration from distributed data owners. Yet, centralizing all data sources to an untrustworthy centralized server will put users' data at risk of privacy leakage or regulation violation. Federated Learning (FL) is a de facto decentralized learning framework that enables knowledge aggregation from distributed users without exposing private data. Though promising advances are witnessed for FL, new challenges are emerging when integrating FL with the rising needs and opportunities in data mining, graph analytics, foundation models, generative AI, and new interdisciplinary applications in science. By hosting this workshop, we aim to attract a broad range of audiences, including researchers and practitioners from academia and industry interested in the emergent challenges in FL. As an effort to advance the fundamental development of FL, this workshop will encourage ideas exchange on the trustworthiness, scalability, and robustness of distributed data mining and graph analytics and their emergent challenges.

Deep Learning has facilitated various high-stakes applications such as crime detection, urban planning, drug discovery, and healthcare. Its continuous success hinges on learning from massive data in miscellaneous sources, ranging from data with independent distributions to graph-structured data capturing intricate inter-sample relationships. Scaling up the data access requires global collaboration from distributed data owners. Yet, centralizing all data sources to an untrustworthy centralized server will put users' data at risk of privacy leakage or regulation violation. Federated Learning (FL) is a de facto decentralized learning framework that enables knowledge aggregation from distributed users without exposing private data. Though promising advances are witnessed for FL, new challenges are emerging when integrating FL with the rising needs and opportunities in data mining, graph analytics, foundation models, generative AI, and new interdisciplinary applications in science. By hosting this workshop, we aim to attract a broad range of audiences, including researchers and practitioners from academia and industry interested in the emergent challenges in FL. As an effort to advance the fundamental development of FL, this workshop will encourage ideas exchange on the trustworthiness, scalability, and robustness of distributed data mining and graph analytics and their emergent challenges.

The past decade has witnessed wide applications of machine learning to various domains for decision-making, including crime detection, urban planning, drug discovery, and health monitoring, which benefited from surging data resources. As data collection in real-world applications is often done in different locations, being able to mine and discover knowledge from distributed data sources is an essential requirement for building powerful predictive models. However, directly uploading all data sources to an untrustworthy centralized data server for learning will lead to risks of privacy leakage. Federated Learning (FL) emerges as a decentralized learning framework that aggregates knowledge from distributed data without centralizing them, hence mitigating privacy risks. By hosting this workshop, we aim to attract a broad spectrum of audiences, including researchers and practitioners from academia and industry interested in the latest advances in FL. As an effort to advance the fundamental development of FL in data mining, this workshop will encourage ideas exchange on the trustworthiness, scalability, robustness, and broad applications of FL.

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the promising prospects of reinforcement learning in numerous domains such as robotics and game-playing, transfer learning has arisen to tackle various challenges faced by reinforcement learning, by transferring knowledge from external expertise to facilitate the efficiency and effectiveness of the learning process. In this survey, we systematically investigate the recent progress of transfer learning approaches in the context of deep reinforcement learning. Specifically, we provide a framework for categorizing the state-of-the-art transfer learning approaches, under which we analyze their goals, methodologies, compatible reinforcement learning backbones, and practical applications. We also draw connections between transfer learning and other relevant topics from the reinforcement learning perspective and explore their potential challenges that await future research progress.

Mobile devices have emerged as the most popular platforms to access information. However, they have also become a major concern of privacy violation and previous researches have demonstrated various approaches to infer user privacy based on mobile devices. In this paper, we study the electromagnetic (EM) emission of a laptop that could be harvested by a commercial-off-the-shelf (COTS) mobile device, e.g., a smartphone. We proposeMagAttack, which exploits the electromagnetic side channel of a laptop to guess user activities, i.e., application launching and application operation. The key insight ofMagAttackis that applications are discrepant in essence due to the different compositions of instructions, which can be reflected on the CPU power consumption, and thus the corresponding EM emissions.MagAttackis challenging since that EM signals are noisy due to the dynamics of applications and the limited sampling rate of the built-in magnetometers in COTS mobile devices. We overcome these challenges and convert noisy coarse-grained EM signals to robust fine-grained features. We implementMagAttackon both an iOS and an Android smartphone without any hardware modification, and evaluate its performance with 30 popular applications, 30 YouTube videos, and 50 top websites in China. The results demonstrate thatMagAttackcan recognize aforementioned 30 applications with an average accuracy of 98.6 percent, and identify which video out of the 30 candidates being played with an average accuracy of 97.5 percent and visiting which website among the 50 candidates with an average accuracy of 90.4 percent.

Reinforcement learning (RL) has demonstrated its superiority in solving sequential decision-making problems. However, heavy dependence on immediate reward feedback impedes the wide application of RL. On the other hand, imitation learning (IL) tackles RL without relying on environmental supervision by leveraging external demonstrations. In practice, however, collecting sufficient expert demonstrations can be prohibitively expensive, yet the quality of demonstrations typically limits the performance of the learning policy. To address a practical scenario, in this work, we propose Self-Adaptive Imitation Learning (SAIL), which, provided with a few demonstrations from a sub-optimal teacher, can perform well in RL tasks with extremely delayed rewards, where the only reward feedback is trajectory-wise ranking. SAIL bridges the advantages of IL and RL by interactively exploiting the demonstrations to catch up with the teacher and exploring the environment to yield demonstrations that surpass the teacher. Extensive empirical results show that not only does SAIL significantly improve the sample efficiency, but it also leads to higher asymptotic performance across different continuous control tasks, compared with the state-of-the-art.

Unsupervised Domain Adaptation (UDA) provides a promising solution for learning without supervision, which transfers knowledge from relevant source domains with accessible labeled training data. Existing UDA solutions hinge on clean training data with a short-tail distribution from the source domain, which can be fragile when the source domain data is corrupted either inherently or via adversarial attacks. In this work, we propose an effective framework to address the challenges of UDA from corrupted source domains in a principled manner. Specifically, we perform knowledge ensemble from multiple domain-invariant models that are learned on random partitions of training data. To further address the distribution shift from the source to the target domain, we refine each of the learned models via mutual information maximization, which adaptively obtains the predictive information of the target domain with high confidence. Extensive empirical studies demonstrate that the proposed approach is robust against various types of poisoned data attacks while achieving high asymptotic performance on the target domain.

The rise of Federated Learning (FL) is bringing machine learning to edge computing by utilizing data scattered across edge devices. However, the heterogeneity of edge network topologies and the uncertainty of wireless transmission are two major obstructions of FL’s wide application in edge computing, leading to prohibitive convergence time and high communication cost. In this work, we propose an FL scheme to address both challenges simultaneously. Specifically, we enable edge devices to learn self-distilled neural networks that are readily prunable to arbitrary sizes, which capture the knowledge of the learning domain in a nested and progressive manner. Not only does our approach tackle system heterogeneity by serving edge devices with varying model architectures, but it also alleviates the issue of connection uncertainty by allowing transmitting part of the model parameters under faulty network connections, without wasting the contributing knowledge of the transmitted parameters. Extensive empirical studies show that under system heterogeneity and network instability, our approach demonstrates significant resilience and higher communication efficiency compared to the state-of-the-art.

Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a prerequisite is satisfied. Moreover, the ensemble knowledge is not fully utilized to guide local model learning, which may in turn affect the quality of the aggregated model. Inspired by the prior art, we propose a data-free knowledge distillation approach to address heterogeneous FL, where the server learns a lightweight generator to ensemble user information in a data-free manner, which is then broadcasted to users, regulating local training using the learned knowledge as an inductive bias. Empirical studies powered by theoretical implications show that our approach facilitates FL with better generalization performance using fewer communication rounds, compared with the state-of-the-art.

Federated learning is a distributed learning framework that is communication efficient and provides protection over participating users' raw training data. One outstanding challenge of federate learning comes from the users' heterogeneity, and learning from such data may yield biased and unfair models for minority groups. While adversarial learning is commonly used in centralized learning for mitigating bias, there are significant barriers when extending it to the federated framework. In this work, we study these barriers and address them by proposing a novel approach Federated Adversarial DEbiasing (FADE). FADE does not require users' sensitive group information for debiasing and offers users the freedom to opt-out from the adversarial component when privacy or computational costs become a concern. We show that ideally, FADE can attain the same global optimality as the one by the centralized algorithm. We then analyze when its convergence may fail in practice and propose a simple yet effective method to address the problem. Finally, we demonstrate the effectiveness of the proposed framework through extensive empirical studies, including the problem settings of unsupervised domain adaptation and fair learning. Our codes and pre-trained models are available at: https://github.com/illidanlab/FADE.

Cloud providers have started to deploy various FPGA accelerators in their datacenters because the performance of many applications can be significantly improved by implementing their core routines in FPGAs. In conventional datacenters with FPGA accelerated servers, if a tenant wants to use FPGA accelerators, it requests for a VM instance residing in a server equipped with an FPGA accelerator. This paradigm to integrate FPGA into Cloud leads to poor resource sharing of the precious FPGA resources. In this paper, we propose FPGAPooling, an FPAG-enabled Cloud system where all FPGA accelerators are managed as a single resource pool and shared among all VMs. For a VM, instead of requesting the Cloud to run the VM on an FPGA accelerated server, at run time, when a VM needs to use FPGA acceleration, it requests an FPGA accelerator from the pool. After the VM finishes using the FPGA accelerator, it releases the FPGA accelerator back to the pool. We design a centralized scheduler to handle acceleration requests from VMs and assign each request to an idle FPGA accelerator at run time; We implemented a system prototype on IBM's OpenPower Cloud system. The key challenging of FPGAPooling is scheduling. We designed and implemented a group of scheduling algorithms for the FPGAPooling system. With extensive evaluations on both a small testbed and a large-scale simulation, we found that our algorithms can improve the average and tail job completion time by up to 7 and 4 times, respectively.

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging because of the lack of expert action guidance. In both conventional IL and LfO, distribution matching is at the heart of their foundation. Traditional distribution matching approaches are sample-costly which depend on on-policy transitions for policy learning. Towards sample-efficiency, some off-policy solutions have been proposed, which, however, either lack comprehensive theoretical justifications or depend on the guidance of expert actions. In this work, we propose a sample-efficient LfO approach which enables off-policy optimization in a principled manner. To further accelerate the learning procedure, we regulate the policy update with an inverse action model, which assists distribution matching from the perspective of mode-covering. Extensive empirical results on challenging locomotion tasks indicate that our approach is comparable with state-of-the-art in terms of both sample-efficiency and asymptotic performance.

Mobile devices have emerged as the most popular platforms to access information. However, they have also become a major concern of privacy violation and previous researches have demonstrated various approaches to infer user privacy based on mobile devices. In this paper, we study a new side channel of a laptop that could be harvested by a commercial-off-the-shelf (COTS) mobile device, eg, a smartphone. We propose MagAttack, which exploits the electromagnetic (EM) side channel of a laptop to infer user activities, i.e., application launching and application operation. The key insight of MagAttack is that applications are discrepant in essence due to the different compositions of instructions, which can be reflected on the CPU power consumption, and thus the corresponding EM emissions. MagAttack is challenging since that EM signals are noisy due to the dynamics of applications and the limited sampling rate of the built-in magnetometers in COTS mobile devices. We overcome these challenges and convert noisy coarse-grained EM signals to robust fine-grained features. We implement MagAttack on both an iOS and an Android smartphone without any hardware modification, and evaluate its performance with 13 popular applications and 50 top websites in China. The results demonstrate that MagAttack can recognize aforementioned 13 applications with an average accuracy of 98.6%, and figure out the visiting operation among 50 websites with an average accuracy of 84.7%.

Recently, handwriting recognition approaches has been widely applied to Human-Computer Interface (HCI) applications. The emergence of the novel mobile terminals urges a more man-machine friendly interface mode. The previous air-writing recognition approaches have been accomplished by virtue of cameras and sensors. However, the vision based approaches are susceptible to the light condition and sensor based methods have disadvantages in deployment and highcost. The latest researches have demonstrated that the pervasive wireless signals can be used to identify different gestures. In this paper, we attempt to utilize channel state information (CSI) derived from wireless signals to realize the device-free air-write recognition called Wi-Fi. Compared to the gesture recognition, the increased diversity and complexity of characters of the alphabet make it challenging. The Principle Component Analysis (PCA) is used for denoising effectively and the energy indicator derived from the Fast Fourier Transform (FFT) is to detect action continuously. The unique CSI waveform caused by unique writing patterns of 26 letters serve as feature space. Finally, the Hidden Markov model (HMM) is used for character modeling and classification. We conduct experiments in our laboratory and get the average accuracy of the Wi-Fi are 86.75 and 88.74 percent in two writing areas, respectively.

Using FPGA as accelerators is gaining popularity in Cloud computing. Usually, FPGA accelerators in a datacenter are managed as a single resource pool. By issuing a request to this pool, a tenant can transparently access FPGA resources. FPGA requests usually arrive in batches. The objective of scheduling is to minimize the make-span of a given batch of requests, which is the completion time of the entire batch of jobs. As a result, either the responsiveness is improved, or the system throughput is maximized. The key technical challenge is the existence of multiple resource bottlenecks. An FPGA job can be bottlenecked by either computation (i.e., computation-intensive) or network (i.e., network-intensive), and sometimes by both. To the best of our knowledge, this is the first work that minimizes the make-span of batched requests for an FPGA accelerator pool in Cloud computing that considers multiple resource bottlenecks. In this paper, we design several scheduling algorithms to address the challenge. We implement our scheduling algorithms in an IBM Cloud system. We conduct extensive evaluations on both a small scale testbed and a large-scale simulator. Compared with the Shortest-Job-First scheduling, our algorithms can reduce the make-span by 36.25 percent, and improve the system throughput by 36.05 percent.