arXiv subjects

Yige Liu

Publications and source records attributed to Yige Liu.

6 recordsLinked to original sources

arXiv2026

Revisiting Label Inference Attacks in Vertical Federated Learning: Why They Are Vulnerable and How to Defend

Vertical federated learning (VFL) allows an active party with a top model, and multiple passive parties with bottom models to collaborate. In this scenario, passive parties possessing only features may attempt to infer active party's private labels, making label inference attacks (LIAs) a significant threat. Previous LIA studies have claimed that well-trained bottom models can effectively represent labels. However, we demonstrate that this view is misleading and exposes the vulnerability of existing LIAs. By leveraging mutual information, we present the first observation of the "model compensation" phenomenon in VFL. We theoretically prove that, in VFL, the mutual information between layer outputs and labels increases with layer depth, indicating that bottom models primarily extract feature information while the top model handles label mapping. Building on this insight, we introduce task reassignment to show that the success of existing LIAs actually stems from the distribution alignment between features and labels. When this alignment is disrupted, the performance of LIAs declines sharply or even fails entirely. Furthermore, the implications of this insight for defenses are also investigated. We propose a zero-overhead defense technique based on layer adjustment. Extensive experiments across five datasets and five representative model architectures indicate that shifting cut layers forward to increase the proportion of top model layers in the entire model not only improves resistance to LIAs but also enhances other defenses.

cs.LG↗

arXiv2026

Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning

As a distributed collaborative machine learning paradigm, vertical federated learning (VFL) allows multiple passive parties with distinct features and one active party with labels to collaboratively train a model. Although it is known for the privacy-preserving capabilities, VFL still faces significant privacy and security threats from backdoor attacks. Existing backdoor attacks typically involve an attacker implanting a trigger into the model during the training phase and executing the attack by adding the trigger to the samples during the inference phase. However, in this paper, we find that triggers are not essential for backdoor attacks in VFL. In light of this, we disclose a new backdoor attack pathway in VFL by introducing a feature-based triggerless backdoor attack. This attack operates under a more stringent security assumption, where the attacker is honest-but-curious rather than malicious during the training phase. It comprises three modules: label inference for the targeted backdoor attack, poison generation with amplification and perturbation mechanisms, and backdoor execution to implement the attack. Extensive experiments on five benchmark datasets demonstrate that our attack outperforms three baseline backdoor attacks by 2 to 50 times while minimally impacting the main task. Even in VFL scenarios with 32 passive parties and only one set of auxiliary data, our attack maintains high performance. Moreover, when confronted with distinct defense strategies, our attack remains largely unaffected and exhibits strong robustness. We hope that the disclosure of this triggerless backdoor attack pathway will encourage the community to revisit security threats in VFL scenarios and inspire researchers to develop more robust and practical defense strategies.

cs.LG↗

arXiv2025

Mesoscience-based structural theory for heterogeneous gas-solid flows

Quantification of the spatiotemporal dynamics of heterogeneous gas-solid flows is critical for the design, scale-up and optimization of gas-solid reactors. In this article, by using the core concept of mesoscience (the compromise in competition between dominant mechanisms), a mathematically rigorous procedure is proposed to develop a mesoscience-based structural theory for the dynamics of heterogeneous gas-solid flows via describing the physical states corresponding to the realization of dominant mechanisms as the interpenetrating continua, finding the microscale governing equations of gas-solid flow, defining a dominant mechanism indicator function, and finally, performing ensemble averaging to obtain the macroscopic governing equations. It is shown that the theory can be mathematically formulated as partial differential equations (PDE) constrained dynamic optimization, possible closures for the constitutive relationships are then discussed, and numerical validations using a simplified theory are also performed. Present study (i) offers an alternative method to the popular two-fluid model for simulating the spatiotemporal dynamics of heterogeneous gas-solid flows, with the distinct advantage that the constitutive relationships can be developed using the models and correlations that are obtained from homogeneous systems, of course an extra model for the interphase mass transfer rate between dilute phase and dense phase is needed, and the effective numerical solution of PDE-constrained dynamic optimization needs to be explored; and (ii) provides a feasible procedure to formulate concrete mathematical equations from the core concept of mesoscience.

physics.flu-dyn↗

arXiv2024

A critical comparison of the implementation of granular pressure gradient term in Euler-Euler simulation of gas-solid flows

Numerical solution of Euler-Euler model using different in-house, open source and commercial software can generate significantly different results, even when the governing equations and the initial and boundary conditions are exactly same. Unfortunately, the underlying reasons have not been identified yet. In this article, three methods for calculating the granular pressure gradient term are presented for two-fluid model of gas-solid flows and implemented implicitly or explicitly into the solver in OpenFOAM: Method I assumes that the granular pressure gradient is equal to the elastic modulus plus the solid concentration gradient; Method II directly calculates the gradient using a difference scheme; Method III, which is proposed in this work, calculates the gradient as the sum of two partial derivatives: one related to the solid volume fraction and the other related to the granular energy. Obviously, only Methods II and III are consistent with kinetic theory of granular flow. It was found that the difference between all methods is small for bubbling fluidization. While for circulating fluidization, both methods II and III are capable of capturing non-uniform structures and producing superior results over Method I. The contradictory conclusions made from the simulation of different fluidization regimes is due to the different contribution of the term related to the granular energy gradient. Present study concludes that the implementation method of granular pressure gradient may have a significant impact on hydrodynamics and is probably a key factor contributing to the observed differences between different simulation software.

physics.flu-dyn↗

arXiv2024

Center-to-face momentum interpolation and face-to-center flux reconstruction in Euler-Euler simulation of gas-solid flows

In order to resolve the pressure checkerboard field problem with collocated grid, it is essential to employ the momentum interpolation method when formulating the pressure equation, and the flux reconstruction method when updating the cell-centered velocity fields. In this study, we first derive a momentum interpolation method for Euler-Euler simulation of gas-solid flows, which is independent of the time step, the transient term discretization scheme, the under-relaxation factor and the shape of grid; a complete first-order flux reconstruction method is then proposed to update the cell-centered velocities. Their effectiveness are proved by simulating the hydrodynamics of solids settlement, gas-solid fixed bed, bubbling fluidized bed and circulating fluidized bed riser, and then comparing the simulation results to the theoretically known solutions. Their superiority over the standard solver of OpenFOAM in suppressing the high-frequency oscillations and enhancing the smoothness and accuracy is also proved. Finally, the difficulty in fully eliminating the high-frequency oscillations is attributed to the insufficiency of current methods in handling the situations where the independent variables undergo abrupt change.

physics.flu-dyn↗

arXiv2023

Direct reduction of iron-ore with hydrogen in fluidized beds: A coarse-grained CFD-DEM-IBM study

Hydrogen metallurgy technology uses hydrogen as the reducing agent instead of carbon reduction, which is one of the important ways to reduce carbon dioxide emissions and ensure the green and sustainable development of iron and steel industry. Due to the advantages of high gas-solid contact efficiency and outstanding mass and heat transfer, direct reduction of iron ore in fluidized beds has attracted much attention. In this study, a coarse-grained CFD-DEM-IBM solver based on hybrid CPU-GPU computing is developed to simulate the direct reduction process of two kinds of iron ore with hydrogen in fluidized beds, where an unreacted shrinking core model based on multiple reaction paths is used to model the reduction reactions, a coarse-grained model and multiple GPUs enable the significant acceleration of particle computation, and the immersed boundary method (IBM) enables the use of simple mesh even in complex geometries of reactors. The predicted results of particle reduction degree are in good agreement with the experimental values, which proves the correctness of the CFD-DEM-IBM solver. In addition, the effects of reaction kinetic parameters and operating temperature on particle reduction degree are also investigated. Present study provides a method for digital design, optimization and scale-up of ironmaking reactors.

physics.flu-dyn↗