arXiv subjects

Lixiang Li

Publications and source records attributed to Lixiang Li.

11 recordsLinked to original sources

arXiv2024

Parallel Unlearning in Inherited Model Networks

Unlearning is challenging in generic learning frameworks with the continuous growth and updates of models exhibiting complex inheritance relationships. This paper presents a novel unlearning framework that enables fully parallel unlearning among models exhibiting inheritance. We use a chronologically Directed Acyclic Graph (DAG) to capture various unlearning scenarios occurring in model inheritance networks. Central to our framework is the Fisher Inheritance Unlearning (FIUn) method, designed to enable efficient parallel unlearning within the DAG. FIUn utilizes the Fisher Information Matrix (FIM) to assess the significance of model parameters for unlearning tasks and adjusts them accordingly. To handle multiple unlearning requests simultaneously, we propose the Merging-FIM (MFIM) function, which consolidates FIMs from multiple upstream models into a unified matrix. This design supports all unlearning scenarios captured by the DAG, enabling one-shot removal of inherited knowledge while significantly reducing computational overhead. Experiments confirm the effectiveness of our unlearning framework. For single-class tasks, it achieves complete unlearning with 0% accuracy for unlearned labels while maintaining 94.53% accuracy for retained labels. For multi-class tasks, the accuracy is 1.07% for unlearned labels and 84.77% for retained labels. Our framework accelerates unlearning by 99% compared to alternative methods. Code is in https://github.com/MJLee00/Parallel-Unlearning-in-Inherited-Model-Networks.

cs.LG↗

arXiv2024

BlockFUL: Enabling Unlearning in Blockchained Federated Learning

Unlearning in Federated Learning (FL) presents significant challenges, as models grow and evolve with complex inheritance relationships. This complexity is amplified when blockchain is employed to ensure the integrity and traceability of FL, where the need to edit multiple interlinked blockchain records and update all inherited models complicates the process.In this paper, we introduce Blockchained Federated Unlearning (BlockFUL), a novel framework with a dual-chain structure comprising a live chain and an archive chain for enabling unlearning capabilities within Blockchained FL. BlockFUL introduces two new unlearning paradigms, i.e., parallel and sequential paradigms, which can be effectively implemented through gradient-ascent-based and re-training-based unlearning methods. These methods enhance the unlearning process across multiple inherited models by enabling efficient consensus operations and reducing computational costs. Our extensive experiments validate that these methods effectively reduce data dependency and operational overhead, thereby boosting the overall performance of unlearning inherited models within BlockFUL on CIFAR-10 and Fashion-MNIST datasets using AlexNet, ResNet18, and MobileNetV2 models.

cs.CR↗

arXiv2022

On the Usability (In)Security of In-App Browsing Interfaces in Mobile Apps

Due to the frequent encountering of web URLs in various application scenarios (e.g., chatting and email reading), many mobile apps build their in-app browsing interfaces (IABIs) to provide a seamless user experience. Although this achieves user-friendliness by avoiding the constant switching between the subject app and the system built-in browser apps, we find that IABIs, if not well designed or customized, could result in usability security risks. In this paper, we conduct the first empirical study on the usability (in)security of in-app browsing interfaces in both Android and iOS apps. Specifically, we collect a dataset of 25 high-profile mobile apps from five common application categories that contain IABIs, including Facebook and Gmail, and perform a systematic analysis (not end-user study though) that comprises eight carefully designed security tests and covers the entire course of opening, displaying, and navigating an in-app web page. During this process, we obtain three major security findings: (1) about 30% of the tested apps fail to provide enough URL information for users to make informed decisions on opening an URL; (2) nearly all custom IABIs have various problems in providing sufficient indicators to faithfully display an in-app page to users, whereas ten IABIs that are based on Chrome Custom Tabs and SFSafariViewController are generally secure; and (3) only a few IABIs give warnings to remind users of the risk of inputting passwords during navigating a (potentially phishing) login page. Most developers had acknowledged our findings but their willingness and readiness to fix usability issues are rather low compared to fixing technical vulnerabilities, which is a puzzle in usability security research. Nevertheless, to help mitigate risky IABIs and guide future designs, we propose a set of secure IABI design principles.

cs.CR↗

arXiv2021

MELOPPR: Software/Hardware Co-design for Memory-efficient Low-latency Personalized PageRank

Personalized PageRank (PPR) is a graph algorithm that evaluates the importance of the surrounding nodes from a source node. Widely used in social network related applications such as recommender systems, PPR requires real-time responses (latency) for a better user experience. Existing works either focus on algorithmic optimization for improving precision while neglecting hardware implementations or focus on distributed global graph processing on large-scale systems for improving throughput rather than response time. Optimizing low-latency local PPR algorithm with a tight memory budget on edge devices remains unexplored. In this work, we propose a memory-efficient, low-latency PPR solution, namely MeLoPPR, with largely reduced memory requirement and a flexible trade-off between latency and precision. MeLoPPR is composed of stage decomposition and linear decomposition and exploits the node score sparsity: Through stage and linear decomposition, MeLoPPR breaks the computation on a large graph into a set of smaller sub-graphs, that significantly saves the computation memory; Through sparsity exploitation, MeLoPPR selectively chooses the sub-graphs that contribute the most to the precision to reduce the required computation. In addition, through software/hardware co-design, we propose a hardware implementation on a hybrid CPU and FPGA accelerating platform, that further speeds up the sub-graph computation. We evaluate the proposed MeLoPPR on memory-constrained devices including a personal laptop and Xilinx Kintex-7 KC705 FPGA using six real-world graphs. First, MeLoPPR demonstrates significant memory saving by 1.5x to 13.4x on CPU and 73x to 8699x on FPGA. Second, MeLoPPR allows flexible trade-offs between precision and execution time: when the precision is 80%, the speedup on CPU is up to 15x and up to 707x on FPGA; when the precision is around 90%, the speedup is up to 70x on FPGA.

cs.DC↗

arXiv2020

Propagation analysis and prediction of the COVID-19

Based on the official data modeling, this paper studies the transmission process of the Corona Virus Disease 2019 (COVID-19). The error between the model and the official data curve is within 3%. At the same time, it realized forward prediction and backward inference of the epidemic situation, and the relevant analysis help relevant countries to make decisions.

q-bio.PE↗

arXiv2018

Optimal community structure for social contagions

Community structure is an important factor in the behavior of real-world networks because it strongly affects the stability and thus the phase transition order of the spreading dynamics. We here propose a reversible social contagion model of community networks that includes the factor of social reinforcement. In our model an individual adopts a social contagion when the number of received units of information exceeds its adoption threshold. We use mean-field approximation to describe our proposed model, and the results agree with numerical simulations. The numerical simulations and theoretical analyses both indicate that there is a first-order phase transition in the spreading dynamics, and that a hysteresis loop emerges in the system when there is a variety of initially-adopted seeds. We find an optimal community structure that maximizes spreading dynamics. We also find a rich phase diagram with a triple point that separates the no-diffusion phase from the two diffusion phases.

physics.soc-ph↗

arXiv2015

The effect of randomness for dependency map on the robustness of interdependent lattices

For interdependent networks with identity dependency map, percolation is exactly the same with that on a single network and follows a second-order phase transition, while for random dependency, percolation follows a first-order phase transition. In real networks, the dependency relations between networks are neither identical nor completely random. Thus in this paper, we study the influence of randomness for dependency maps on the robustness of interdependent lattice networks. We introduce approximate entropy($ApEn$) as the measure of randomness of the dependency maps. We find that there is critical $ApEn_c$ below which the percolation is continuous, but for larger $ApEn$, it is a first-order transition. With the increment of $ApEn$, the $p_c$ increases until $ApEn$ reaching ${ApEn}_c'$ and then remains almost constant. The time scale of the system shows rich properties as $ApEn$ increases. Our results uncover that randomness is one of the important factors that lead to cascading failures of spatially interdependent networks.

cs.SI↗

arXiv2013

Multiple routes transmitted epidemics on multiplex networks

This letter investigates the multiple routes transmitted epidemic process on multiplex networks. We propose detailed theoretical analysis that allows us to accurately calculate the epidemic threshold and outbreak size. It is found that the epidemic can spread across the multiplex network even if all the network layers are well below their respective epidemic thresholds. Strong positive degree-degree correlation of nodes in multiplex network could lead to a much lower epidemic threshold and a relatively smaller outbreak size. However, the average similarity of neighbors from different layers of nodes has no obvious effect on the epidemic threshold and outbreak size.

cs.SI↗

arXiv2013

Multiple Vectors Propagation of Epidemics in Complex Networks

This letter investigates the epidemic spreading in two-vectors propagation network (TPN). We propose detailed theoretical analysis that allows us to accurately calculate the epidemic threshold and outbreak size. It is found that the epidemics can spread across the TPN even if two sub-single-vector propagation networks (SPNs) of TPN are well below their respective epidemic thresholds. Strong positive degree-degree correlation of nodes in TPN could lead to a much lower epidemic threshold and a relatively smaller outbreak size. However, the average similarity between the neighbors from different SPNs of nodes has no effect on the epidemic threshold and outbreak size.

physics.soc-ph↗

arXiv2013

A secure and effective anonymous authentication scheme for roaming service in global mobility networks

Recently, Mun et al. analyzed Wu et al.'s authentication scheme and proposed a enhanced anonymous authentication scheme for roaming service in global mobility networks. However, through careful analysis, we find that Mun et al.'s scheme is vulnerable to impersonation attacks, off-line password guessing attacks and insider attacks, and cannot provide user friendliness, user's anonymity, proper mutual authentication and local verification. To remedy these weaknesses, in this paper we propose a novel anonymous authentication scheme for roaming service in global mobility networks. Security and performance analyses show the proposed scheme is more suitable for the low-power and resource-limited mobile devices, and is secure against various attacks and has many excellent features.

cs.CR↗

arXiv2011

Effects of gradient coupling on amplitude death in nonidentical oscillators

In this work, we investigate gradient coupling effect on amplitude death in an array of N cou- pled nonidentical oscillators with no-flux boundary conditions and periodic boundary conditions respectively. We find that the effects of gradient coupling on amplitude death in diffusive coupled nonidentical oscillators is quite different between those two boundaries conditions. With no-flux boundary conditions, there is a system size related critical gradient coupling $r_c$ within which the gradient coupling tends to monotonically enlarge the amplitude death domain in the parameter space. With the periodical boundary conditions, there is an optimal gradient coupling constant $r_o$ to realize largest AD domain. The gradient coupling first enlarges then decreases the amplitude death domain of diffusive coupled oscillators. The amplitude death domain of parameter space are analytically predicted for small number of gradient coupled oscillators.

nlin.CD↗