Searcharxiv⌕ Search

arXiv subjects

Kai Li

Publications and source records attributed to Kai Li.

At least 271 records · Page 15Linked to original sources
arXiv2024

Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing

Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy. To enhance data efficiency by sharing parameters across multiple tasks, a common practice segments the network into distinct modules and trains a routing network to recombine these modules into task-specific policies. However, existing routing approaches employ a fixed number of modules for all tasks, neglecting that tasks with varying difficulties commonly require varying amounts of knowledge. This work presents a Dynamic Depth Routing (D2R) framework, which learns strategic skipping of certain intermediate modules, thereby flexibly choosing different numbers of modules for each task. Under this framework, we further introduce a ResRouting method to address the issue of disparate routing paths between behavior and target policies during off-policy training. In addition, we design an automatic route-balancing mechanism to encourage continued routing exploration for unmastered tasks without disturbing the routing of mastered ones. We conduct extensive experiments on various robotics manipulation tasks in the Meta-World benchmark, where D2R achieves state-of-the-art performance with significantly improved learning efficiency.

cs.AI↗
arXiv2024

TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion

Audio-visual speech separation has gained significant traction in recent years due to its potential applications in various fields such as speech recognition, diarization, scene analysis and assistive technologies. Designing a lightweight audio-visual speech separation network is important for low-latency applications, but existing methods often require higher computational costs and more parameters to achieve better separation performance. In this paper, we present an audio-visual speech separation model called Top-Down-Fusion Net (TDFNet), a state-of-the-art (SOTA) model for audio-visual speech separation, which builds upon the architecture of TDANet, an audio-only speech separation method. TDANet serves as the architectural foundation for the auditory and visual networks within TDFNet, offering an efficient model with fewer parameters. On the LRS2-2Mix dataset, TDFNet achieves a performance increase of up to 10\% across all performance metrics compared with the previous SOTA method CTCNet. Remarkably, these results are achieved using fewer parameters and only 28\% of the multiply-accumulate operations (MACs) of CTCNet. In essence, our method presents a highly effective and efficient solution to the challenges of speech separation within the audio-visual domain, making significant strides in harnessing visual information optimally.

cs.SD↗
arXiv2024

Understanding the Security Risks of Decentralized Exchanges by Uncovering Unfair Trades in the Wild

DEX, or decentralized exchange, is a prominent class of decentralized finance (DeFi) applications on blockchains, attracting a total locked value worth tens of billions of USD today. This paper presents the first large-scale empirical study that uncovers unfair trades on popular DEX services on Ethereum and Binance Smart Chain (BSC). By joining and analyzing 60 million transactions, we find 671,400 unfair trades on all six measured DEXes, including Uniswap, Balancer, and Curve. Out of these unfair trades, we attribute 55,000 instances, with high confidence, to token thefts that cause a value loss of more than 3.88 million USD. Furthermore, the measurement study uncovers previously unknown causes of extractable value and real-world adaptive strategies to these causes. Finally, we propose countermeasures to redesign secure DEX protocols and to harden deployed services against the discovered security risks.

cs.CR↗
arXiv2024

Higher-order topological phases in crystalline and non-crystalline systems: a review

In recent years, higher-order topological phases have attracted great interest in various fields of physics. These phases have protected boundary states at lower-dimensional boundaries than the conventional first-order topological phases due to the higher-order bulk-boundary correspondence. In this review, we summarize current research progress on higher-order topological phases in both crystalline and non-crystalline systems. We firstly introduce prototypical models of higher-order topological phases in crystals and their topological characterizations. We then discuss effects of quenched disorder on higher-order topology and demonstrate disorder-induced higher-order topological insulators. We also review the theoretical studies on higher-order topological insulators in amorphous systems without any crystalline symmetry and higher-order topological phases in nonperiodic lattices including quasicrystals, hyperbolic lattices, and fractals, which have no crystalline counterparts. We conclude the review by a summary of experimental realizations of higher-order topological phases and discussions on potential directions for future study.

cond-mat.mes-hall↗
arXiv2024

LEFormer: A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagery

Lake extraction from remote sensing images is challenging due to the complex lake shapes and inherent data noises. Existing methods suffer from blurred segmentation boundaries and poor foreground modeling. This paper proposes a hybrid CNN-Transformer architecture, called LEFormer, for accurate lake extraction. LEFormer contains three main modules: CNN encoder, Transformer encoder, and cross-encoder fusion. The CNN encoder effectively recovers local spatial information and improves fine-scale details. Simultaneously, the Transformer encoder captures long-range dependencies between sequences of any length, allowing them to obtain global features and context information. The cross-encoder fusion module integrates the local and global features to improve mask prediction. Experimental results show that LEFormer consistently achieves state-of-the-art performance and efficiency on the Surface Water and the Qinghai-Tibet Plateau Lake datasets. Specifically, LEFormer achieves 90.86% and 97.42% mIoU on two datasets with a parameter count of 3.61M, respectively, while being 20 minor than the previous best lake extraction method. The source code is available at https://github.com/BastianChen/LEFormer.

cs.CV↗
arXiv2023

6G Network AI Architecture for Everyone-Centric Customized Services

Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

cs.NI↗
arXiv2023

Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference

Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high. Although there exist ways for model pruning or distillation, it is typically required to perform a full round of model training or finetuning procedure in order to obtain a smaller model that satisfies the model size or complexity constraints. Motivated by recent works on dynamic neural networks, we propose a simple way to train a large network and flexibly extract a subnetwork from it given a model size or complexity constraint during inference. We introduce a new way to allow a large model to be trained with dynamic depth and width during the training phase, and after the large model is trained we can select a subnetwork from it with arbitrary depth and width during the inference phase with a relatively better performance compared to training the subnetwork independently from scratch. Experiment results on a music source separation model show that our proposed method can effectively improve the separation performance across different subnetwork sizes and complexities with a single large model, and training the large model takes significantly shorter time than training all the different subnetworks.

cs.LG↗
arXiv2023

Detection and Mitigation of Position Spoofing Attacks on Cooperative UAV Swarm Formations

Detecting spoofing attacks on the positions of unmanned aerial vehicles (UAVs) within a swarm is challenging. Traditional methods relying solely on individually reported positions and pairwise distance measurements are ineffective in identifying the misbehavior of malicious UAVs. This paper presents a novel systematic structure designed to detect and mitigate spoofing attacks in UAV swarms. We formulate the problem of detecting malicious UAVs as a localization feasibility problem, leveraging the reported positions and distance measurements. To address this problem, we develop a semidefinite relaxation (SDR) approach, which reformulates the non-convex localization problem into a convex and tractable semidefinite program (SDP). Additionally, we propose two innovative algorithms that leverage the proximity of neighboring UAVs to identify malicious UAVs effectively. Simulations demonstrate the superior performance of our proposed approaches compared to existing benchmarks. Our methods exhibit robustness across various swarm networks, showcasing their effectiveness in detecting and mitigating spoofing attacks. {\blue Specifically, the detection success rate is improved by up to 65\%, 55\%, and 51\% against distributed, collusion, and mixed attacks, respectively, compared to the benchmarks.

eess.SY↗
arXiv2023

Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach

This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data and achieves both effectiveness and undetectability. By listening to the benign local models and the global model, the attacker extracts the graph structural correlations among the benign local models and the training data features substantiating the models. The attacker then adversarially regenerates the graph structural correlations while maximizing the FL training loss, and subsequently generates malicious local models using the adversarial graph structure and the training data features of the benign ones. A new algorithm is designed to iteratively train the malicious local models using GAE and sub-gradient descent. The convergence of FL under attack is rigorously proved, with a considerably large optimality gap. Experiments show that the FL accuracy drops gradually under the proposed attack and existing defense mechanisms fail to detect it. The attack can give rise to an infection across all benign devices, making it a serious threat to FL.

cs.LG↗
arXiv2023

PanBench: Towards High-Resolution and High-Performance Pansharpening

Pansharpening, a pivotal task in remote sensing, involves integrating low-resolution multispectral images with high-resolution panchromatic images to synthesize an image that is both high-resolution and retains multispectral information. These pansharpened images enhance precision in land cover classification, change detection, and environmental monitoring within remote sensing data analysis. While deep learning techniques have shown significant success in pansharpening, existing methods often face limitations in their evaluation, focusing on restricted satellite data sources, single scene types, and low-resolution images. This paper addresses this gap by introducing PanBench, a high-resolution multi-scene dataset containing all mainstream satellites and comprising 5,898 pairs of samples. Each pair includes a four-channel (RGB + near-infrared) multispectral image of 256x256 pixels and a mono-channel panchromatic image of 1,024x1,024 pixels. To achieve high-fidelity synthesis, we propose a Cascaded Multiscale Fusion Network (CMFNet) for Pansharpening. Extensive experiments validate the effectiveness of CMFNet. We have released the dataset, source code, and pre-trained models in the supplementary, fostering further research in remote sensing.

cs.CV↗
arXiv2023

Are research contributions assigned differently under the two contributorship classification systems in PLoS ONE?

Contributorship statements have been effective at recording granular author contributions in research articles and have been broadly used to understand how labor is divided across research teams. However, one major limitation in existing empirical studies is that two classification systems have been adopted, especially from its most important data source, journals published by the Public Library of Science (PLoS). This research aims to address this limitation by developing a mapping scheme between the two systems and using it to understand whether there are differences in the assignment of contribution by authors under the two systems. We use all research articles published in PLoS ONE between 2012 to 2020, divided into two five-year publication windows centered by the shift of the classification systems in 2016. Our results show that most tasks (except for writing- and resource-related tasks) are used similarly under the two systems. Moreover, notable differences between how researchers used the two systems are also examined and discussed. This research offers an important foundation for empirical research on division of labor in the future, by enabling a larger dataset that crosses both, and potentially other, classification systems.

cs.DL↗
arXiv2023

Towards Understanding and Characterizing the Arbitrage Bot Scam In the Wild

This paper presents the first comprehensive analysis of an emerging cryptocurrency scam named "arbitrage bot" disseminated on online social networks. The scam revolves around Decentralized Exchanges (DEX) arbitrage and aims to lure victims into executing a so-called "bot contract" to steal funds from them. To collect the scam at a large scale, we developed a fully automated scam detection system named CryptoScamHunter, which continuously collects YouTube videos and automatically detects scams. Meanwhile, CryptoScamHunter can download the source code of the bot contract from the provided links and extract the associated scam cryptocurrency address. Through deploying CryptoScamHunter from Jun. 2022 to Jun. 2023, we have detected 10,442 arbitrage bot scam videos published from thousands of YouTube accounts. Our analysis reveals that different strategies have been utilized in spreading the scam, including crafting popular accounts, registering spam accounts, and using obfuscation tricks to hide the real scam address in the bot contracts. Moreover, from the scam videos we have collected over 800 malicious bot contracts with source code and extracted 354 scam addresses. By further expanding the scam addresses with a similar contract matching technique, we have obtained a total of 1,697 scam addresses. Through tracing the transactions of all scam addresses on the Ethereum mainnet and Binance Smart Chain, we reveal that over 25,000 victims have fallen prey to this scam, resulting in a financial loss of up to 15 million USD. Overall, our work sheds light on the dissemination tactics and censorship evasion strategies adopted in the arbitrage bot scam, as well as on the scale and impact of such a scam on online social networks and blockchain platforms, emphasizing the urgent need for effective detection and prevention mechanisms against such fraudulent activity.

cs.CR↗
arXiv2023

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

The rapid progress in open-source large language models (LLMs) is significantly advancing AI development. Extensive efforts have been made before model release to align their behavior with human values, with the primary goal of ensuring their helpfulness and harmlessness. However, even carefully aligned models can be manipulated maliciously, leading to unintended behaviors, known as "jailbreaks". These jailbreaks are typically triggered by specific text inputs, often referred to as adversarial prompts. In this work, we propose the generation exploitation attack, an extremely simple approach that disrupts model alignment by only manipulating variations of decoding methods. By exploiting different generation strategies, including varying decoding hyper-parameters and sampling methods, we increase the misalignment rate from 0% to more than 95% across 11 language models including LLaMA2, Vicuna, Falcon, and MPT families, outperforming state-of-the-art attacks with $30\times$ lower computational cost. Finally, we propose an effective alignment method that explores diverse generation strategies, which can reasonably reduce the misalignment rate under our attack. Altogether, our study underscores a major failure in current safety evaluation and alignment procedures for open-source LLMs, strongly advocating for more comprehensive red teaming and better alignment before releasing such models. Our code is available at https://github.com/Princeton-SysML/Jailbreak_LLM.

cs.CL↗
arXiv2023

Consistency Regularization for Generalizable Source-free Domain Adaptation

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. This oversight leads to overfitting issues and constrains the model's generalization ability. In this paper, we propose a consistency regularization framework to develop a more generalizable SFDA method, which simultaneously boosts model performance on both target training and testing datasets. Our method leverages soft pseudo-labels generated from weakly augmented images to supervise strongly augmented images, facilitating the model training process and enhancing the generalization ability of the adapted model. To leverage more potentially useful supervision, we present a sampling-based pseudo-label selection strategy, taking samples with severer domain shift into consideration. Moreover, global-oriented calibration methods are introduced to exploit global class distribution and feature cluster information, further improving the adaptation process. Extensive experiments demonstrate our method achieves state-of-the-art performance on several SFDA benchmarks, and exhibits robustness on unseen testing datasets.

cs.CV↗
arXiv2023

Gastro-Intestinal Tract Segmentation Using an Explainable 3D Unet

In treating gastrointestinal cancer using radiotherapy, the role of the radiation oncologist is to administer high doses of radiation, through x-ray beams, toward the tumor while avoiding the stomach and intestines. With the advent of precise radiation treatment technology such as the MR-Linac, oncologists can visualize the daily positions of the tumors and intestines, which may vary day to day. Before delivering radiation, radio oncologists must manually outline the position of the gastrointestinal organs in order to determine position and direction of the x-ray beam. This is a time consuming and labor intensive process that may substantially prolong a patient's treatment. A deep learning (DL) method can automate and expedite the process. However, many deep neural networks approaches currently in use are black-boxes which lack interpretability which render them untrustworthy and impractical in a healthcare setting. To address this, an emergent field of AI known as Explainable AI (XAI) may be incorporated to improve the transparency and viability of a model. This paper proposes a deep learning pipeline that incorporates XAI to address the challenges of organ segmentation.

eess.IV↗
arXiv2023

Reconstruction of inhomogeneous media by an iteration algorithm with a learned projector

This paper is concerned with the inverse problem of reconstructing an inhomogeneous medium from the acoustic far-field data at a fixed frequency in two dimensions. This inverse problem is severely ill-posed (and also strongly nonlinear), and certain regularization strategy is thus needed. However, it is difficult to select an appropriate regularization strategy which should enforce some a priori information of the unknown scatterer. To address this issue, we plan to use a deep learning approach to learn some a priori information of the unknown scatterer from certain ground truth data, which is then combined with a traditional iteration method to solve the inverse problem. Specifically, we propose a deep learning-based iterative reconstruction algorithm for the inverse problem, based on a repeated application of a deep neural network and the iteratively regularized Gauss-Newton method (IRGNM). Our deep neural network (called the learned projector in this paper) mainly focuses on learning the a priori information of the shape of the unknown contrast with a normalization technique in the training process and is trained to act like a projector which is helpful for projecting the solution into some feasible region. Extensive numerical experiments show that our reconstruction algorithm provides good reconstruction results even for the high contrast case and has a satisfactory generalization ability.

math.NA↗
arXiv2023

Downlink Channel Covariance Matrix Reconstruction for FDD Massive MIMO Systems with Limited Feedback

The downlink channel covariance matrix (CCM) acquisition is the key step for the practical performance of massive multiple-input and multiple-output (MIMO) systems, including beamforming, channel tracking, and user scheduling. However, this task is challenging in the popular frequency division duplex massive MIMO systems with Type I codebook due to the limited channel information feedback. In this paper, we propose a novel formulation that leverages the structure of the codebook and feedback values for an accurate estimation of the downlink CCM. Then, we design a cutting plane algorithm to consecutively shrink the feasible set containing the downlink CCM, enabled by the careful design of pilot weighting matrices. Theoretical analysis shows that as the number of communication rounds increases, the proposed cutting plane algorithm can recover the ground-truth CCM. Numerical results are presented to demonstrate the superior performance of the proposed algorithm over the existing benchmark in CCM reconstruction.

eess.SP↗
arXiv2023

PruMUX: Augmenting Data Multiplexing with Model Compression

As language models increase in size by the day, methods for efficient inference are critical to leveraging their capabilities for various applications. Prior work has investigated techniques like model pruning, knowledge distillation, and data multiplexing to increase model throughput without sacrificing accuracy. In this paper, we combine two such methods -- structured pruning and data multiplexing -- to compound the speedup gains obtained by either method. Our approach, PruMUX, obtains up to 7.5-29.5X throughput improvement over BERT-base model with accuracy threshold from 80% to 74%. We further study various combinations of parameters (such as sparsity and multiplexing factor) in the two techniques to provide a comprehensive analysis of the tradeoff between accuracy and throughput in the resulting models. We then propose Auto-PruMUX, a meta-level model that can predict the high-performance parameters for pruning and multiplexing given a desired accuracy loss budget, providing a practical method to leverage the combination effectively.

cs.LG↗