arXiv subjects

Ming Hu

Publications and source records attributed to Ming Hu.

At least 145 records · Page 8Linked to original sources

arXiv2023

Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models

Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible backdoor attacks. This paper investigates a critical and unexplored aspect of text-to-image (T2I) diffusion models - their potential vulnerability to backdoor attacks via personalization. Our study focuses on a zero-day backdoor vulnerability prevalent in two families of personalization methods, epitomized by Textual Inversion and DreamBooth.Compared to traditional backdoor attacks, our proposed method can facilitate more precise, efficient, and easily accessible attacks with a lower barrier to entry. We provide a comprehensive review of personalization in T2I diffusion models, highlighting the operation and exploitation potential of this backdoor vulnerability. To be specific, by studying the prompt processing of Textual Inversion and DreamBooth, we have devised dedicated backdoor attacks according to the different ways of dealing with unseen tokens and analyzed the influence of triggers and concept images on the attack effect. Through comprehensive empirical study, we endorse the utilization of the nouveau-token backdoor attack due to its impressive effectiveness, stealthiness, and integrity, markedly outperforming the legacy-token backdoor attack.

cs.CV↗

arXiv2023

Scalable Multiuser Immersive Communications with Multi-numerology and Mini-slot

This paper studies multiuser immersive communications networks in which different user equipment may demand various extended reality (XR) services. In such heterogeneous networks, time-frequency resource allocation needs to be more adaptive since XR services are usually multi-modal and latency-sensitive. To this end, we develop a scalable time-frequency resource allocation method based on multi-numerology and mini-slot. To appropriately determining the discrete parameters of multi-numerology and mini-slot for multiuser immersive communications, the proposed method first presents a novel flexible time-frequency resource block configuration, then it leverages the deep reinforcement learning to maximize the total quality-of-experience (QoE) under different users' QoE constraints. The results confirm the efficiency and scalability of the proposed time-frequency resource allocation method.

cs.ET↗

arXiv2023

AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems

Federated Learning (FL) enables collaborative learning of large-scale distributed clients without data sharing. However, due to the disparity of computing resources among massive mobile computing devices, the performance of traditional homogeneous model-based Federated Learning (FL) is seriously limited. On the one hand, to achieve model training in all the diverse clients, mobile computing systems can only use small low-performance models for collaborative learning. On the other hand, devices with high computing resources cannot train a high-performance large model with their insufficient raw data. To address the resource-constrained problem in mobile computing systems, we present a novel heterogeneous FL approach named AdapterFL, which uses a model reassemble strategy to facilitate collaborative training of massive heterogeneous mobile devices adaptively. Specifically, we select multiple candidate heterogeneous models based on the computing performance of massive mobile devices and then divide each heterogeneous model into two partitions. By reassembling the partitions, we can generate models with varied sizes that are combined by the partial parameters of the large model with the partial parameters of the small model. Using these reassembled models for FL training, we can train the partial parameters of the large model using low-performance devices. In this way, we can alleviate performance degradation in large models due to resource constraints. The experimental results show that AdapterFL can achieve up to 12\% accuracy improvement compared to the state-of-the-art heterogeneous federated learning methods in resource-constrained scenarios.

cs.LG↗

arXiv2023

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

The application of deep learning to nursing procedure activity understanding has the potential to greatly enhance the quality and safety of nurse-patient interactions. By utilizing the technique, we can facilitate training and education, improve quality control, and enable operational compliance monitoring. However, the development of automatic recognition systems in this field is currently hindered by the scarcity of appropriately labeled datasets. The existing video datasets pose several limitations: 1) these datasets are small-scale in size to support comprehensive investigations of nursing activity; 2) they primarily focus on single procedures, lacking expert-level annotations for various nursing procedures and action steps; and 3) they lack temporally localized annotations, which prevents the effective localization of targeted actions within longer video sequences. To mitigate these limitations, we propose NurViD, a large video dataset with expert-level annotation for nursing procedure activity understanding. NurViD consists of over 1.5k videos totaling 144 hours, making it approximately four times longer than the existing largest nursing activity datasets. Notably, it encompasses 51 distinct nursing procedures and 177 action steps, providing a much more comprehensive coverage compared to existing datasets that primarily focus on limited procedures. To evaluate the efficacy of current deep learning methods on nursing activity understanding, we establish three benchmarks on NurViD: procedure recognition on untrimmed videos, procedure and action recognition on trimmed videos, and action detection. Our benchmark and code will be available at \url{https://github.com/minghu0830/NurViD-benchmark}.

cs.CV↗

arXiv2023

Efficient synthesis of Vitamin D3 in a 3D ultraviolet photochemical microreactor fabricated using an ultrafast laser

Large-scale, high-precision, and high-transparency microchannels hold great potential for developing high-performance continuous-flow photochemical reactions. We demonstrate ultrafast laser-enabled fabrication of 3D microchannel reactors in ultraviolet (UV) grade fused silica which exhibit high transparency under the illumination of UV light sources of wavelengths well below 300 nm with excellent mixing efficiency. With the fabricated glass microchannel reactors, we demonstrate continuous-flow UV photochemical synthesis of vitamin D3 with low power consumption of the UV light sources.

physics.app-ph↗

arXiv2023

MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding

Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammal-net.github.io.

cs.CV↗

arXiv2023

Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches

The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e.g., autonomous driving, content moderation, biometric authentication, medical imaging) in the physical world. To address this problem in a trustworthy way, proposals have been made for certified patch defenses that ensure the robustness of classification models and prevent future patch attacks from breaching the defense. State-of-the-art certified defenses can be compatible with any model architecture, as well as achieve high clean and certified accuracy. Although the methods are adaptive to arbitrary patch positions, they inevitably need to access the size of the adversarial patch, which is unreasonable and impractical in real-world attack scenarios. To improve the feasibility of the architecture-agnostic certified defense in a black-box setting (i.e., position and size of the patch are both unknown), we propose a novel two-stage Iterative Black-box Certified Defense method, termed IBCD.In the first stage, it estimates the patch size in a search-based manner by evaluating the size relationship between the patch and mask with pixel masking. In the second stage, the accuracy results are calculated by the existing white-box certified defense methods with the estimated patch size. The experiments conducted on two popular model architectures and two datasets verify the effectiveness and efficiency of IBCD.

cs.CV↗

arXiv2023

Real-time spectroscopic monitoring of continuous synthesis of zinc oxide nanostructures in femtosecond laser fabricated 3D microfluidic microchannels with integrated on-chip fiber probe array

Materials synthesis in a microfluidic environment enables the flexible and controllable production of various types of nanostructures which are of great potential in the fields of chemistry, environmental science, bioengineering, and medicine. Here, we demonstrate on-chip simultaneous continuous-flow synthesis and in-situ spectrum diagnosis of zinc oxide (ZnO) nanomaterials using a femtosecond-fabricated three-dimensional microchannel reactor integrated with an array of optical fiber probes. The microchannel reactor including 3D concentration gradient generators followed by 3D micromixing units provides high-efficiency manipulation of reactants with different concentrations as well as parallel reaction dynamics in an autonomous manner. The integrated optical fiber probe array allows precise and parallel spectropic detection in different microchannels with high spatial and temporal resolutions for screening the synthetic conditions. The synthesized ZnO nanostructures can be tailored in size, shape, and morphology by tuning the flow rates and reactant concentrations based on the spectroscopic signals detected with the fiber probe array.

physics.app-ph↗

arXiv2022

Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints

Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts' heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700\% compared to FTCP, one of the latest structure generators and by more than 45\% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1,869 materials out of 2,000 are successfully optimized and deposited into the Carolina Materials Database \url{www.carolinamatdb.org}, of which 39.6\% have negative formation energy and 5.3\% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability.

cond-mat.mtrl-sci↗

arXiv2022

HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation

Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centralized global model aggregation. FL suffers from model inaccuracy and slow convergence due to the model heterogeneity of the AIoT devices involved. Although various existing methods try to solve the bottleneck of the model heterogeneity problem, most of them improve the accuracy of heterogeneous models in a coarse-grained manner, which makes it still a great challenge to deploy large-scale AIoT devices. To alleviate the negative impact of this problem and take full advantage of the diversity of each heterogeneous model, we propose an efficient framework named HierarchyFL, which uses a small amount of public data for efficient and scalable knowledge across a variety of differently structured models. By using self-distillation and our proposed ensemble library, each hierarchical model can intelligently learn from each other on cloud servers. Experimental results on various well-known datasets show that HierarchyFL can not only maximize the knowledge sharing among various heterogeneous models in large-scale AIoT systems, but also greatly improve the model performance of each involved heterogeneous AIoT device.

cs.LG↗

arXiv2022

GitFL: Adaptive Asynchronous Federated Learning using Version Control

As a promising distributed machine learning paradigm that enables collaborative training without compromising data privacy, Federated Learning (FL) has been increasingly used in AIoT (Artificial Intelligence of Things) design. However, due to the lack of efficient management of straggling devices, existing FL methods greatly suffer from the problems of low inference accuracy and long training time. Things become even worse when taking various uncertain factors (e.g., network delays, performance variances caused by process variation) existing in AIoT scenarios into account. To address this issue, this paper proposes a novel asynchronous FL framework named GitFL, whose implementation is inspired by the famous version control system Git. Unlike traditional FL, the cloud server of GitFL maintains a master model (i.e., the global model) together with a set of branch models indicating the trained local models committed by selected devices, where the master model is updated based on both all the pushed branch models and their version information, and only the branch models after the pull operation are dispatched to devices. By using our proposed Reinforcement Learning (RL)-based device selection mechanism, a pulled branch model with an older version will be more likely to be dispatched to a faster and less frequently selected device for the next round of local training. In this way, GitFL enables both effective control of model staleness and adaptive load balance of versioned models among straggling devices, thus avoiding the performance deterioration. Comprehensive experimental results on well-known models and datasets show that, compared with state-of-the-art asynchronous FL methods, GitFL can achieve up to 2.64X training acceleration and 7.88% inference accuracy improvements in various uncertain scenarios.

cs.LG↗

arXiv2022

Algorithmic Decision-Making Safeguarded by Human Knowledge

Commercial AI solutions provide analysts and managers with data-driven business intelligence for a wide range of decisions, such as demand forecasting and pricing. However, human analysts may have their own insights and experiences about the decision-making that is at odds with the algorithmic recommendation. In view of such a conflict, we provide a general analytical framework to study the augmentation of algorithmic decisions with human knowledge: the analyst uses the knowledge to set a guardrail by which the algorithmic decision is clipped if the algorithmic output is out of bound, and seems unreasonable. We study the conditions under which the augmentation is beneficial relative to the raw algorithmic decision. We show that when the algorithmic decision is asymptotically optimal with large data, the non-data-driven human guardrail usually provides no benefit. However, we point out three common pitfalls of the algorithmic decision: (1) lack of domain knowledge, such as the market competition, (2) model misspecification, and (3) data contamination. In these cases, even with sufficient data, the augmentation from human knowledge can still improve the performance of the algorithmic decision.

stat.ML↗

arXiv2022

FedMR: Fedreated Learning via Model Recombination

As a promising privacy-preserving machine learning method, Federated Learning (FL) enables global model training across clients without compromising their confidential local data. However, existing FL methods suffer from the problem of low inference performance for unevenly distributed data, since most of them rely on Federated Averaging (FedAvg)-based aggregation. By averaging model parameters in a coarse manner, FedAvg eclipses the individual characteristics of local models, which strongly limits the inference capability of FL. Worse still, in each round of FL training, FedAvg dispatches the same initial local models to clients, which can easily result in stuck-at-local-search for optimal global models. To address the above issues, this paper proposes a novel and effective FL paradigm named FedMR (Federating Model Recombination). Unlike conventional FedAvg-based methods, the cloud server of FedMR shuffles each layer of collected local models and recombines them to achieve new models for local training on clients. Due to the fine-grained model recombination and local training in each FL round, FedMR can quickly figure out one globally optimal model for all the clients. Comprehensive experimental results demonstrate that, compared with state-of-the-art FL methods, FedMR can significantly improve the inference accuracy without causing extra communication overhead.

cs.LG↗

arXiv2022

FedEntropy: Efficient Device Grouping for Federated Learning Using Maximum Entropy Judgment

Along with the popularity of Artificial Intelligence (AI) and Internet-of-Things (IoT), Federated Learning (FL) has attracted steadily increasing attentions as a promising distributed machine learning paradigm, which enables the training of a central model on for numerous decentralized devices without exposing their privacy. However, due to the biased data distributions on involved devices, FL inherently suffers from low classification accuracy in non-IID scenarios. Although various device grouping method have been proposed to address this problem, most of them neglect both i) distinct data distribution characteristics of heterogeneous devices, and ii) contributions and hazards of local models, which are extremely important in determining the quality of global model aggregation. In this paper, we present an effective FL method named FedEntropy with a novel dynamic device grouping scheme, which makes full use of the above two factors based on our proposed maximum entropy judgement heuristic.Unlike existing FL methods that directly aggregate local models returned from all the selected devices, in one FL round FedEntropy firstly makes a judgement based on the pre-collected soft labels of selected devices and then only aggregates the local models that can maximize the overall entropy of these soft labels. Without collecting local models that are harmful for aggregation, FedEntropy can effectively improve global model accuracy while reducing the overall communication overhead. Comprehensive experimental results on well-known benchmarks show that, FedEntropy not only outperforms state-of-the-art FL methods in terms of model accuracy and communication overhead, but also can be integrated into them to enhance their classification performance.

cs.LG↗

arXiv2022

Model-Contrastive Learning for Backdoor Defense

Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification. Although there exist various defense methods that can effectively erase backdoors from DNNs, they greatly suffer from both high Attack Success Rate (ASR) and a non-negligible loss in Benign Accuracy (BA). Inspired by the observation that a backdoored DNN tends to form a new cluster in its feature spaces for poisoned data, in this paper we propose a novel two-stage backdoor defense method, named MCLDef, based on Model-Contrastive Learning (MCL). In the first stage, our approach performs trigger inversion based on trigger synthesis, where the resultant trigger can be used to generate poisoned data. In the second stage, under the guidance of MCL and our defined positive and negative pairs, MCLDef can purify the backdoored model by pulling the feature representations of poisoned data towards those of their clean data counterparts. Due to the shrunken cluster of poisoned data, the backdoor formed by end-to-end supervised learning is eliminated. Comprehensive experimental results show that, with only 5% of clean data, MCLDef significantly outperforms state-of-the-art defense methods by up to 95.79% reduction in ASR, while in most cases the BA degradation can be controlled within less than 2%. Our code is available at https://github.com/WeCanShow/MCL.

cs.LG↗

arXiv2022

Genetic programming-based learning of carbon interatomic potential for materials discovery

Efficient and accurate interatomic potential functions are critical to computational study of materials while searching for structures with desired properties. Traditionally, potential functions or energy landscapes are designed by experts based on theoretical or heuristic knowledge. Here, we propose a new approach to leverage strongly typed parallel genetic programming (GP) for potential function discovery. We use a multi-objective evolutionary algorithm with NSGA-III selection to optimize individual age, fitness, and complexity through symbolic regression. With a DFT dataset of 863 unique carbon allotrope configurations drawn from 858 carbon structures, the generated potentials are able to predict total energies within $\pm 7.70$ eV at low computational cost while generalizing well across multiple carbon structures. Our code is open source and available at \url{http://www.github.com/usccolumbia/mlpotential

cond-mat.mtrl-sci↗

arXiv2022

Model-Free Assortment Pricing with Transaction Data

We study the problem when a firm sets prices for products based on the transaction data, i.e., which product past customers chose from an assortment and what were the historical prices that they observed. Our approach does not impose a model on the distribution of the customers' valuations and only assumes, instead, that purchase choices satisfy incentive-compatible constraints. The individual valuation of each past customer can then be encoded as a polyhedral set, and our approach maximizes the worst-case revenue assuming that new customers' valuations are drawn from the empirical distribution implied by the collection of such polyhedra. We show that the optimal prices in this setting can be approximated at any arbitrary precision by solving a compact mixed-integer linear program. Moreover, we study the single-product case and relate it to the traditional model-based approach. We also design three approximation strategies that are of low computational complexity and interpretable. Comprehensive numerical studies based on synthetic and real data suggest that our pricing approach is uniquely beneficial when the historical data has a limited size or is susceptible to model misspecification.

math.OC↗

arXiv2022

3D large-scale fused silica microfluidic chips enabled by hybrid laser microfabrication for continuous-flow UV photochemical synthesis

We demonstrate a hybrid laser microfabrication approach, which combines the technical merits of ultrafast laser-assisted chemical etching and carbon dioxide laser-induced in-situ melting, for centimeter-scale and bonding-free fabrication of 3D complex hollow microstructures in fused silica glass. With the developed approach, large-scale fused silica microfluidic chips with integrated 3D cascaded micromixing units can be reliably manufactured. High-performance on-chip mixing and continuous-flow photochemical synthesis under UV LEDs irradiation at ~280 nm were demonstrated using the manufactured chip, indicating a powerful capability for versatile fabrication of highly transparent all-glass microfluidic reactors for on-chip photochemical synthesis.

physics.app-ph↗