arXiv subjects

Lichun Li

Publications and source records attributed to Lichun Li.

17 recordsLinked to original sources

arXiv2026

A data-driven model-free physical-informed deep operator network for solving nonlinear dynamic system

The existing physical-informed Deep Operator Networks are mostly based on either the well-known mathematical formula of the system or huge amounts of data for different scenarios. However, in some cases, it is difficult to get the exact mathematical formula and vast amounts of data in some dynamic systems, we can only get a few experimental data or limited mathematical information. To address the cases, we propose a data-driven model-free physical-informed Deep Operator Network (DeepOnet) framework to learn the nonlinear dynamic systems from few available data. We first explore the short-term dependence of the available data and use a surrogate machine learning model to extract the short-term dependence. Then, the surrogate machine learning model is incorporated into the DeepOnet as the physical information part. Then, the constructed DeepOnet is trained to simulate the system's dynamic response for given control inputs and initial conditions. Numerical experiments on different systems confirm that our DeepOnet framework learns to approximate the dynamic response of some nonlinear dynamic systems effectively.

eess.SP↗

arXiv2025

Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained increasing attention for its ability to address data heterogeneity. However, most existing pFL methods assume that each client's data follows a single distribution and learn one client-level personalized model for each client. This assumption often fails in practice, where a single client may possess data from multiple sources or domains, resulting in significant intra-client heterogeneity and suboptimal performance. To tackle this challenge, we propose pFedBayesPT, a fine-grained instance-wise pFL framework based on visual prompt tuning. Specifically, we formulate instance-wise prompt generation from a Bayesian perspective and model the prompt posterior as an implicit distribution to capture diverse visual semantics. We derive a variational training objective under the semi-implicit variational inference framework. Extensive experiments on benchmark datasets demonstrate that pFedBayesPT consistently outperforms existing pFL methods under both feature and label heterogeneity settings.

cs.LG↗

arXiv2025

Privacy-Preserving Inference for Quantized BERT Models

With the increasing deployment of generative machine learning models in privacy-sensitive domains such as healthcare and personalized services, ensuring secure inference has become a critical challenge. Secure multi-party computation (MPC) enables privacy-preserving model inference but suffers from high communication and computation overhead. The main bottleneck lies in the expensive secure evaluation of floating-point operations. Quantization offers a promising solution by converting floating-point operations into lower-precision integer computations, significantly reducing overhead. However, existing MPC-based quantized inference methods either rely on public quantization parameters-posing privacy risks-or suffer from inefficiencies, particularly in handling nonlinear functions such as activations and softmax. In this work, we propose a fine-grained, layer-wise quantization scheme and support 1-bit weight fully connected layers in a secure setting. We design a multi-input lookup table protocol to evaluate softmax efficiently and securely. Furthermore, we use dual secret sharing schemes and perform precision conversions via lookup tables, eliminating truncation overhead entirely. Experimental evaluation on BERT-base models demonstrates that our approach achieves up to $8\times$ speedup compared to Lu \emph{et al}. (NDSS 25), $9\times$ speedup compared to Gupta \emph{et al}. (PETS 24) and $22 \times$ speedup compared to Knott \emph{et al}. (NeurIPS 21).

cs.LG↗

arXiv2025

From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling

Financial markets exhibit highly dynamic and complex behaviors shaped by both historical price trajectories and exogenous narratives, such as news, policy interpretations, and social media sentiment. The heterogeneity in these data and the diverse insight of investors introduce biases that complicate the modeling of market dynamics. Unlike prior work, this paper explores the potential of bull and bear regimes in investor-driven market dynamics. Through empirical analysis on real-world financial datasets, we uncover a dynamic relationship between bias variation and behavioral adaptation, which enhances trend prediction under evolving market conditions. To model this mechanism, we propose the Bias to Behavior from Bull-Bear Dynamics model (B4), a unified framework that jointly embeds temporal price sequences and external contextual signals into a shared latent space where opposing bull and bear forces naturally emerge, forming the foundation for bias representation. Within this space, an inertial pairing module pairs temporally adjacent samples to preserve momentum, while the dual competition mechanism contrasts bullish and bearish embeddings to capture behavioral divergence. Together, these components allow B4 to model bias-driven asymmetry, behavioral inertia, and market heterogeneity. Experimental results on real-world financial datasets demonstrate that our model not only achieves superior performance in predicting market trends but also provides interpretable insights into the interplay of biases, investor behaviors, and market dynamics.

cs.LG↗

arXiv2025

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models

The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yielding privacy risks for both model and data owners. One promising solution, called offsite-tuning (OT), is proposed to address these challenges, where a weaker emulator is compressed from the original model and further fine-tuned with adapter to enhance privacy. However, the existing OT-based methods require high computational costs and lack theoretical analysis. This paper introduces a novel OT approach based on gradient-preserving compression, named GradOT. By analyzing the OT problem through the lens of optimization, we propose a method that selectively applies compression techniques such as rank compression and channel pruning, preserving the gradients of fine-tuned adapters while ensuring privacy. Extensive experiments demonstrate that our approach surpasses existing OT methods, both in terms of privacy protection and model performance. Our method provides a theoretical foundation for OT and offers a practical, training-free solution for offsite-tuning of large-scale LLMs.

cs.CL↗

arXiv2025

VIRGOS: Secure Graph Convolutional Network on Vertically Split Data from Sparse Matrix Decomposition

Securely computing graph convolutional networks (GCNs) is critical for applying their analytical capabilities to privacy-sensitive data like social/credit networks. Multiplying a sparse yet large adjacency matrix of a graph in GCN--a core operation in training/inference--poses a performance bottleneck in secure GCNs. Consider a GCN with $|V|$ nodes and $|E|$ edges; it incurs a large $O(|V|^2)$ communication overhead. Modeling bipartite graphs and leveraging the monotonicity of non-zero entry locations, we propose a co-design harmonizing secure multi-party computation (MPC) with matrix sparsity. Our sparse matrix decomposition transforms an arbitrary sparse matrix into a product of structured matrices. Specialized MPC protocols for oblivious permutation and selection multiplication are then tailored, enabling our secure sparse matrix multiplication ($(SM)^2$) protocol, optimized for secure multiplication of these structured matrices. Together, these techniques take $O(|E|)$ communication in constant rounds. Supported by $(SM)^2$, we present Virgos, a secure 2-party framework that is communication-efficient and memory-friendly on standard vertically-partitioned graph datasets. Performance of Virgos has been empirically validated across diverse network conditions.

cs.CR↗

arXiv2024

ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression

Offsite-tuning is a privacy-preserving method for tuning large language models (LLMs) by sharing a lossy compressed emulator from the LLM owners with data owners for downstream task tuning. This approach protects the privacy of both the model and data owners. However, current offsite tuning methods often suffer from adaptation degradation, high computational costs, and limited protection strength due to uniformly dropping LLM layers or relying on expensive knowledge distillation. To address these issues, we propose ScaleOT, a novel privacy-utility-scalable offsite-tuning framework that effectively balances privacy and utility. ScaleOT introduces a novel layerwise lossy compression algorithm that uses reinforcement learning to obtain the importance of each layer. It employs lightweight networks, termed harmonizers, to replace the raw LLM layers. By combining important original LLM layers and harmonizers in different ratios, ScaleOT generates emulators tailored for optimal performance with various model scales for enhanced privacy protection. Additionally, we present a rank reduction method to further compress the original LLM layers, significantly enhancing privacy with negligible impact on utility. Comprehensive experiments show that ScaleOT can achieve nearly lossless offsite tuning performance compared with full fine-tuning while obtaining better model privacy.

cs.CL↗

arXiv2024

The Communication-Friendly Privacy-Preserving Machine Learning against Malicious Adversaries

With the increasing emphasis on privacy regulations, such as GDPR, protecting individual privacy and ensuring compliance have become critical concerns for both individuals and organizations. Privacy-preserving machine learning (PPML) is an innovative approach that allows for secure data analysis while safeguarding sensitive information. It enables organizations to extract valuable insights from data without compromising privacy. Secure multi-party computation (MPC) is a key tool in PPML, as it allows multiple parties to jointly compute functions without revealing their private inputs, making it essential in multi-server environments. We address the performance overhead of existing maliciously secure protocols, particularly in finite rings like $\mathbb{Z}_{2^\ell}$, by introducing an efficient protocol for secure linear function evaluation. We implement our maliciously secure MPC protocol on GPUs, significantly improving its efficiency and scalability. We extend the protocol to handle linear and non-linear layers, ensuring compatibility with a wide range of machine-learning models. Finally, we comprehensively evaluate machine learning models by integrating our protocol into the workflow, enabling secure and efficient inference across simple and complex models, such as convolutional neural networks (CNNs).

cs.CR↗

arXiv2024

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models

Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks, primarily due to their potential to significantly reduce memory and computational overheads. However, a common limitation in most PEFT approaches is their application of a uniform architectural design across all layers. This uniformity involves identical trainable modules and ignores the varying importance of each layer, leading to sub-optimal fine-tuning results. To overcome the above limitation and obtain better performance, we develop a novel approach, Importance-aware Sparse Tuning (IST), to fully utilize the inherent sparsity and select the most important subset of full layers with effective layer-wise importance scoring. The proposed IST is a versatile and plug-and-play technique compatible with various PEFT methods that operate on a per-layer basis. By leveraging the estimated importance scores, IST dynamically updates these selected layers in PEFT modules, leading to reduced memory demands. We further provide theoretical proof of convergence and empirical evidence of superior performance to demonstrate the advantages of IST over uniform updating strategies. Extensive experiments on a range of LLMs, PEFTs, and downstream tasks substantiate the effectiveness of our proposed method, showcasing IST's capacity to enhance existing layer-based PEFT methods. Our code is available at https://github.com/Kaiseem/IST.

cs.CL↗

arXiv2022

Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning

Secure multi-party computation enables multiple mutually distrusting parties to perform computations on data without revealing the data itself, and has become one of the core technologies behind privacy-preserving machine learning. In this work, we present several improved privacy-preserving protocols for both linear and non-linear layers in machine learning. For linear layers, we present an extended beaver triple protocol for bilinear maps that significantly reduces communication of convolution layer. For non-linear layers, we introduce novel protocols for computing the sigmoid and softmax function. Both functions are essential building blocks for machine learning training of classification tasks. Our protocols are both more scalable and robust than prior constructions, and improves runtime performance by 3-17x. Finally, we introduce Morse-STF, an end-to-end privacy-preserving system for machine learning training that leverages all these improved protocols. Our system achieves a 1.8x speedup on logistic regression and 3.9-4.9x speedup on convolutional neural networks compared to prior state-of-the-art systems.

cs.CR↗

arXiv2021

LP Formulations of sufficient statistic based strategies in Finite Horizon Two-Player Zero-Sum Stochastic Bayesian games

This paper studies two-player zero-sum stochastic Bayesian games where each player has its own dynamic state that is unknown to the other player. Using typical techniques, we provide the recursive formulas and sufficient statistics in both the primal game and its dual games. It's also shown that with a specific initial parameter, the optimal strategy of one player in a dual game is also the optimal strategy of the player in the primal game. To deal with the long finite Bayesian game we have provided an algorithm to compute the sub-optimal strategies of the players step by step to avoid the LP complexity. For this, we computed LPs to find the special initial parameters in the dual games and update the sufficient statistics of the dual games. The performance analysis has provided an upper bound on the performance difference between the optimal and suboptimal strategies. The main results are demonstrated in a security problem of underwater sensor networks.

cs.GT↗

arXiv2021

MPC Protocol for G-module and its Application in Secure Compare and ReLU

Secure comparison and secure selection are two fundamental MPC (secure Multi-Party Computation) protocols. One important application of these protocols is the secure ReLU and DReLU computation in privacy preserving deep learning. In this paper, we introduce G-module, a mathematics tool, to re-design such protocols. In mathematics, given a group G, a G-module is an abelian group M on which G acts compatibly with the abelian group structure on M. We design three secure protocols for three G-module operations. i.e. "G-module action", "Cross G-module action" and "G-module recover". As far as we know, this is the first work on secure G-module operations. Based on them, we design secure comparison, selection, ReLU and DReLU protocols, which improve communication efficiency by 2X to 10X compared with state of arts. Our protocols are very computation efficient too. They do not require public key operations or any other expensive operations.

cs.CR↗

arXiv2019

Smart Jammer and LTE Network Strategies in An Infinite-Horizon Zero-Sum Repeated Game with Asymmetric and Incomplete Information

LTE/LTE-Advanced networks are known to be vulnerable to denial-of-service and loss-of-service attacks from smart jammers. In this article, the interaction between a smart jammer and LTE network is modeled as an infinite-horizon, zero-sum, asymmetric repeated game. The smart jammer and eNode B are modeled as the informed and the uninformed player, respectively. The main purpose of this article is to construct efficient suboptimal strategies for both players that can be used to solve the above-mentioned infinite-horizon repeated game with asymmetric and incomplete information. It has been shown in game-theoretic literature that security strategies provide optimal solution in zero-sum games. It is also shown that both players' security strategies in an infinite-horizon asymmetric game depend only on the history of the informed player's actions. However, fixed-sized sufficient statistics are needed for both players to solve the above-mentioned game efficiently. The smart jammer uses its evolving belief state as the fixed-sized sufficient statistics for the repeated game. Whereas, the LTE network (uninformed player) uses worst-case regret of its security strategy and its anti-discounted update as the fixed-sized sufficient statistics. Although fixed-sized sufficient statistics are employed by both players, optimal security strategy computation in {\lambda}-discounted asymmetric games is still hard to perform because of non-convexity. Hence, the problem is convexified in this article by devising `approximated' security strategies for both players that are based on approximated optimal game value. However, `approximated' strategies require full monitoring. Therefore, a simplistic yet effective `expected' strategy is also constructed for the LTE network that does not require full monitoring. The simulation results show that the smart jammer plays non-revealing and misleading strategies.

cs.GT↗

arXiv2017

Efficient Strategy Computation in Zero-Sum Asymmetric Repeated Games

Zero-sum asymmetric games model decision making scenarios involving two competing players who have different information about the game being played. A particular case is that of nested information, where one (informed) player has superior information over the other (uninformed) player. This paper considers the case of nested information in repeated zero-sum games and studies the computation of strategies for both the informed and uninformed players for finite-horizon and discounted infinite-horizon nested information games. For finite-horizon settings, we exploit that for both players, the security strategy, and also the opponent's corresponding best response depend only on the informed player's history of actions. Using this property, we refine the sequence form, and formulate an LP computation of player strategies that is linear in the size of the uninformed player's action set. For the infinite-horizon discounted game, we construct LP formulations to compute the approximated security strategies for both players, and provide a bound on the performance difference between the approximated security strategies and the security strategies. Finally, we illustrate the results on a network interdiction game between an informed system administrator and uniformed intruder.

cs.GT↗

arXiv2017

An LP Approach for Solving Two-Player Zero-Sum Repeated Bayesian Games

This paper studies two-player zero-sum repeated Bayesian games in which every player has a private type that is unknown to the other player, and the initial probability of the type of every player is publicly known. The types of players are independently chosen according to the initial probabilities, and are kept the same all through the game. At every stage, players simultaneously choose actions, and announce their actions publicly. For finite horizon cases, an explicit linear program is provided to compute players' security strategies. Moreover, based on the existing results in [1], this paper shows that a player's sufficient statistics, which is independent of the strategy of the other player, consists of the belief over the player's own type, the regret with respect to the other player's type, and the stage. Explicit linear programs are provided to compute the initial regrets, and the security strategies that only depends on the sufficient statistics. For discounted cases, following the same idea in the finite horizon, this paper shows that a player's sufficient statistics consists of the belief of the player's own type and the anti-discounted regret with respect to the other player's type. Besides, an approximated security strategy depending on the sufficient statistics is provided, and an explicit linear program to compute the approximated security strategy is given. This paper also obtains a bound on the performance difference between the approximated security strategy and the security strategy.

cs.GT↗

arXiv2017

Iterative Computation of Security Strategies of Matrix Games with Growing Action Set

This paper studies how to efficiently update the saddle-point strategy, or security strategy of one player in a matrix game when the other player develops new actions in the game. It is well known that the saddle-point strategy of one player can be computed by solving a linear program. Developing a new action will add a new constraint to the existing LP. Therefore, our problem becomes how to solve the new LP with a new constraint efficiently. Considering the potentially huge number of constraints, which corresponds to the large size of the other player's action set, we use shadow vertex simplex method, whose computational complexity is lower than linear with respect to the size of the constraints, as the basis of our iterative algorithm. We first rebuild the main theorems in shadow vertex method with relaxed assumption to make sure such method works well in our model, then analyze the probability that the old optimum remains optimal in the new LP, and finally provides the iterative shadow vertex method whose computational complexity is shown to be strictly less than that of shadow vertex method. The simulation results demonstrates our main results about the probability of re-computing the optimum and the computational complexity of the iterative shadow vertex method.

cs.GT↗

arXiv2017

Security Strategies of Both Players in Asymmetric Information Zero-Sum Stochastic Games with an Informed Controller

This paper considers a zero-sum two-player asymmetric information stochastic game where only one player knows the system state, and the transition law is controlled by the informed player only. For the informed player, it has been shown that the security strategy only depends on the belief and the current stage. We provide LP formulations whose size is only linear in the size of the uninformed player's action set to compute both history based and belief based security strategies. For the uninformed player, we focus on the regret, the difference between 0 and the future payoff guaranteed by the uninformed player in every possible state. Regret is a real vector of the same size as the belief, and depends only on the action of the informed player and the strategy of the uninformed player. This paper shows that the uninformed player has a security strategy that only depends on the regret and the current stage. LP formulations are then given to compute the history based security strategy, the regret at every stage, and the regret based security strategy. The size of the LP formulations are again linear in the size of the uninformed player action set. Finally, an intrusion detection problem is studied to demonstrate the main results in this paper.

cs.GT↗