arXiv subjects

Hanpin Wang

Publications and source records attributed to Hanpin Wang.

At least 19 recordsLinked to original sources

arXiv2026

Probabilistic Mechanism Design in Diffusion Auctions

A diffusion auction refers to a selling process conducted over a social network, where each participant submits a bid and may invite other potential buyers to join the auction. Although various mechanisms have been proposed, none of them can simultaneously achieve incentive compatibility, non-negative revenue, and approximate efficiency with a constant approximation bound. In this paper, we propose the Probabilistic Diffusion Mechanism (PDM), a novel mechanism tailored for path graphs, which satisfies all three desired properties. We further extend PDM to general network structures through a map $f$, resulting in the $f$-PDM mechanism, which preserves the key properties of the original design. Beyond these, when $f$ satisfies properties such as breadth-first order, $f$-PDM also ensures Sybil-proofness and provides approximate revenue. Furthermore, to address buyer collusion, we introduce a modified version of the mechanism that balances collusion-proofness with revenue approximation. Finally, we extend the design to multi-unit diffusion auctions -- a more challenging setting -- and propose a simple yet effective mechanism, Multi-Unit PDM (MUPDM), that achieves approximate efficiency while maintaining IC. Moreover, we design Sybil-Proof MUPDM (SP-MUPDM) to resist Sybil attacks in the multi-item scenario.

cs.GT↗

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↗

arXiv2026

Differentiable Rule Induction from Raw Sequence Inputs

Rule learning-based models are widely used in highly interpretable scenarios due to their transparent structures. Inductive logic programming (ILP), a form of machine learning, induces rules from facts while maintaining interpretability. Differentiable ILP models enhance this process by leveraging neural networks to improve robustness and scalability. However, most differentiable ILP methods rely on symbolic datasets, facing challenges when learning directly from raw data. Specifically, they struggle with explicit label leakage: The inability to map continuous inputs to symbolic variables without explicit supervision of input feature labels. In this work, we address this issue by integrating a self-supervised differentiable clustering model with a novel differentiable ILP model, enabling rule learning from raw data without explicit label leakage. The learned rules effectively describe raw data through its features. We demonstrate that our method intuitively and precisely learns generalized rules from time series and image data.

cs.AI↗

arXiv2025

MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output

Currently, medical vision language models are widely used in medical vision question answering tasks. However, existing models are confronted with two issues: for input, the model only relies on text instructions and lacks direct understanding of visual clues in the image; for output, the model only gives text answers and lacks connection with key areas in the image. To address these issues, we propose a unified medical vision language model MIMO, with visual referring Multimodal Input and pixel grounding Multimodal Output. MIMO can not only combine visual clues and textual instructions to understand complex medical images and semantics, but can also ground medical terminologies in textual output within the image. To overcome the scarcity of relevant data in the medical field, we propose MIMOSeg, a comprehensive medical multimodal dataset including 895K samples. MIMOSeg is constructed from four different perspectives, covering basic instruction following and complex question answering with multimodal input and multimodal output. We conduct experiments on several downstream medical multimodal tasks. Extensive experimental results verify that MIMO can uniquely combine visual referring and pixel grounding capabilities, which are not available in previous models.

cs.CV↗

arXiv2025

MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language Models

Recent advances in multimodal large language models (MLLMs) have significantly improved medical AI, enabling it to unify the understanding of visual and textual information. However, as medical knowledge continues to evolve, it is critical to allow these models to efficiently update outdated or incorrect information without retraining from scratch. Although textual knowledge editing has been widely studied, there is still a lack of systematic benchmarks for multimodal medical knowledge editing involving image and text modalities. To fill this gap, we present MedMKEB, the first comprehensive benchmark designed to evaluate the reliability, generality, locality, portability, and robustness of knowledge editing in medical multimodal large language models. MedMKEB is built on a high-quality medical visual question-answering dataset and enriched with carefully constructed editing tasks, including counterfactual correction, semantic generalization, knowledge transfer, and adversarial robustness. We incorporate human expert validation to ensure the accuracy and reliability of the benchmark. Extensive single editing and sequential editing experiments on state-of-the-art general and medical MLLMs demonstrate the limitations of existing knowledge-based editing approaches in medicine, highlighting the need to develop specialized editing strategies. MedMKEB will serve as a standard benchmark to promote the development of trustworthy and efficient medical knowledge editing algorithms.

cs.AI↗

arXiv2025

DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment

Blind image quality assessment (BIQA) methods often incorporate auxiliary tasks to improve performance. However, existing approaches face limitations due to insufficient integration and a lack of flexible uncertainty estimation, leading to suboptimal performance. To address these challenges, we propose a multitasks-based Deep Evidential Fusion Network (DEFNet) for BIQA, which performs multitask optimization with the assistance of scene and distortion type classification tasks. To achieve a more robust and reliable representation, we design a novel trustworthy information fusion strategy. It first combines diverse features and patterns across sub-regions to enhance information richness, and then performs local-global information fusion by balancing fine-grained details with coarse-grained context. Moreover, DEFNet exploits advanced uncertainty estimation technique inspired by evidential learning with the help of normal-inverse gamma distribution mixture. Extensive experiments on both synthetic and authentic distortion datasets demonstrate the effectiveness and robustness of the proposed framework. Additional evaluation and analysis are carried out to highlight its strong generalization capability and adaptability to previously unseen scenarios.

cs.CV↗

arXiv2024

Differentially Private Approval-Based Committee Voting

In this paper, we investigate tradeoffs among differential privacy (DP) and several representative axioms for approval-based committee voting, including justified representation, proportional justified representation, extended justified representation, Pareto efficiency, and Condorcet criterion. Without surprise, we demonstrate that all of these axioms are incompatible with DP, and thus establish both upper and lower bounds for their two-way tradeoffs with DP. Furthermore, we provide upper and lower bounds for three-way tradeoffs among DP and every pairwise combination of such axioms, revealing that although these axioms are compatible without DP, their optimal levels under DP cannot be simultaneously achieved. Our results quantify the effect of DP on the satisfaction and compatibility of the axioms in approval-based committee voting, which can provide insights for designing voting rules that possess both privacy and axiomatic properties.

cs.GT↗

arXiv2023

Trading Off Voting Axioms for Privacy

In this paper, we investigate tradeoffs among differential privacy (DP) and several important voting axioms: Pareto efficiency, SD-efficiency, PC-efficiency, Condorcet consistency, and Condorcet loser criterion. We provide upper and lower bounds on the two-way tradeoffs between DP and each axiom. We also provide upper and lower bounds on three-way tradeoffs among DP and every pairwise combination of all the axioms, showing that, while the axioms are compatible without DP, their upper bounds cannot be achieved simultaneously under DP. Our results illustrate the effect of DP on the satisfaction and compatibility of voting axioms.

cs.GT↗

arXiv2023

First-Choice Maximality Meets Ex-ante and Ex-post Fairness

For the assignment problem where multiple indivisible items are allocated to a group of agents given their ordinal preferences, we design randomized mechanisms that satisfy first-choice maximality (FCM), i.e., maximizing the number of agents assigned their first choices, together with Pareto efficiency (PE). Our mechanisms also provide guarantees of ex-ante and ex-post fairness. The generalized eager Boston mechanism is ex-ante envy-free, and ex-post envy-free up to one item (EF1). The generalized probabilistic Boston mechanism is also ex-post EF1, and satisfies ex-ante efficiency instead of fairness. We also show that no strategyproof mechanism satisfies ex-post PE, EF1, and FCM simultaneously. In doing so, we expand the frontiers of simultaneously providing efficiency and both ex-ante and ex-post fairness guarantees for the assignment problem.

cs.GT↗

arXiv2023

A separation logic for sequences in pointer programs and its decidability

Separation logic and its variants can describe various properties on pointer programs. However, when it comes to properties on sequences, one may find it hard to formalize. To deal with properties on variable-length sequences and multilevel data structures, we propose sequence-heap separation logic which integrates sequences into logical reasoning on heap-manipulated programs. Quantifiers over sequence variables and singleton heap storing sequence (sequence singleton heap) are new members in our logic. Further, we study the satisfiability problem of two fragments. The propositional fragment of sequence-heap separation logic is decidable, and the fragment with 2 alternations on program variables and 1 alternation on sequence variables is undecidable. In addition, we explore boundaries between decidable and undecidable fragments of the logic with prenex normal form.

cs.LO↗

arXiv2022

Differentially Private Condorcet Voting

Designing private voting rules is an important and pressing problem for trustworthy democracy. In this paper, under the framework of differential privacy, we propose a novel famliy of randomized voting rules based on the well-known Condorcet method, and focus on three classes of voting rules in this family: Laplacian Condorcet method ($\CMLAP_\lambda$), exponential Condorcet method ($\CMEXP_\lambda$), and randomized response Condorcet method ($\CMRR_\lambda$), where $\lambda$ represents the level of noise. We prove that all of our rules satisfy absolute monotonicity, lexi-participation, probabilistic Pareto efficiency, approximate probabilistic Condorcet criterion, and approximate SD-strategyproofness. In addition, $\CMRR_\lambda$ satisfies (non-approximate) probabilistic Condorcet criterion, while $\CMLAP_\lambda$ and $\CMEXP_\lambda$ satisfy strong lexi-participation. Finally, we regard differential privacy as a voting axiom, and discuss its relations to other axioms.

cs.GT↗

arXiv2022

Learning First-Order Rules with Differentiable Logic Program Semantics

Learning first-order logic programs (LPs) from relational facts which yields intuitive insights into the data is a challenging topic in neuro-symbolic research. We introduce a novel differentiable inductive logic programming (ILP) model, called differentiable first-order rule learner (DFOL), which finds the correct LPs from relational facts by searching for the interpretable matrix representations of LPs. These interpretable matrices are deemed as trainable tensors in neural networks (NNs). The NNs are devised according to the differentiable semantics of LPs. Specifically, we first adopt a novel propositionalization method that transfers facts to NN-readable vector pairs representing interpretation pairs. We replace the immediate consequence operator with NN constraint functions consisting of algebraic operations and a sigmoid-like activation function. We map the symbolic forward-chained format of LPs into NN constraint functions consisting of operations between subsymbolic vector representations of atoms. By applying gradient descent, the trained well parameters of NNs can be decoded into precise symbolic LPs in forward-chained logic format. We demonstrate that DFOL can perform on several standard ILP datasets, knowledge bases, and probabilistic relation facts and outperform several well-known differentiable ILP models. Experimental results indicate that DFOL is a precise, robust, scalable, and computationally cheap differentiable ILP model.

cs.AI↗

arXiv2021

Favoring Eagerness for Remaining Items: Designing Efficient, Fair, and Strategyproof Mechanisms

In the assignment problem, the goal is to assign indivisible items to agents who have ordinal preferences, efficiently and fairly, in a strategyproof manner. In practice, first-choice maximality, i.e., assigning a maximal number of agents their top items, is often identified as an important efficiency criterion and measure of agents' satisfaction. In this paper, we propose a natural and intuitive efficiency property, favoring-eagerness-for-remaining-items (FERI), which requires that each item is allocated to an agent who ranks it highest among remaining items, thereby implying first-choice maximality. Using FERI as a heuristic, we design mechanisms that satisfy ex-post or ex-ante variants of FERI together with combinations of other desirable properties of efficiency (Pareto-efficiency), fairness (strong equal treatment of equals and sd-weak-envy-freeness), and strategyproofness (sd-weak-strategyproofness). We also explore the limits of FERI mechanisms in providing stronger efficiency, fairness, or strategyproofness guarantees through impossibility results.

cs.GT↗

arXiv2021

StarVQA: Space-Time Attention for Video Quality Assessment

The attention mechanism is blooming in computer vision nowadays. However, its application to video quality assessment (VQA) has not been reported. Evaluating the quality of in-the-wild videos is challenging due to the unknown of pristine reference and shooting distortion. This paper presents a novel \underline{s}pace-\underline{t}ime \underline{a}ttention network fo\underline{r} the \underline{VQA} problem, named StarVQA. StarVQA builds a Transformer by alternately concatenating the divided space-time attention. To adapt the Transformer architecture for training, StarVQA designs a vectorized regression loss by encoding the mean opinion score (MOS) to the probability vector and embedding a special vectorized label token as the learnable variable. To capture the long-range spatiotemporal dependencies of a video sequence, StarVQA encodes the space-time position information of each patch to the input of the Transformer. Various experiments are conducted on the de-facto in-the-wild video datasets, including LIVE-VQC, KoNViD-1k, LSVQ, and LSVQ-1080p. Experimental results demonstrate the superiority of the proposed StarVQA over the state-of-the-art. Code and model will be available at: https://github.com/DVL/StarVQA.

cs.CV↗

arXiv2020

Multi-type Resource Allocation with Partial Preferences

We propose multi-type probabilistic serial (MPS) and multi-type random priority (MRP) as extensions of the well known PS and RP mechanisms to the multi-type resource allocation problem (MTRA) with partial preferences. In our setting, there are multiple types of divisible items, and a group of agents who have partial order preferences over bundles consisting of one item of each type. We show that for the unrestricted domain of partial order preferences, no mechanism satisfies both sd-efficiency and sd-envy-freeness. Notwithstanding this impossibility result, our main message is positive: When agents' preferences are represented by acyclic CP-nets, MPS satisfies sd-efficiency, sd-envy-freeness, ordinal fairness, and upper invariance, while MRP satisfies ex-post-efficiency, sd-strategy-proofness, and upper invariance, recovering the properties of PS and RP.

cs.AI↗

arXiv2020

Probabilistic Serial Mechanism for Multi-Type Resource Allocation

In multi-type resource allocation (MTRA) problems, there are p $\ge$ 2 types of items, and n agents, who each demand one unit of items of each type, and have strict linear preferences over bundles consisting of one item of each type. For MTRAs with indivisible items, our first result is an impossibility theorem that is in direct contrast to the single type (p = 1) setting: No mechanism, the output of which is always decomposable into a probability distribution over discrete assignments (where no item is split between agents), can satisfy both sd-efficiency and sd-envy-freeness. To circumvent this impossibility result, we consider the natural assumption of lexicographic preference, and provide an extension of the probabilistic serial (PS), called lexicographic probabilistic serial (LexiPS).We prove that LexiPS satisfies sd-efficiency and sd-envy-freeness, retaining the desirable properties of PS. Moreover, LexiPS satisfies sd-weak-strategyproofness when agents are not allowed to misreport their importance orders. For MTRAs with divisible items, we show that the existing multi-type probabilistic serial (MPS) mechanism satisfies the stronger efficiency notion of lexi-efficiency, and is sd-envy-free under strict linear preferences, and sd-weak-strategyproof under lexicographic preferences. We also prove that MPS can be characterized both by leximin-ptimality and by item-wise ordinal fairness, and the family of eating algorithms which MPS belongs to can be characterized by no-generalized-cycle condition.

cs.GT↗

arXiv2019

Reasoning about Block-based Cloud Storage Systems

Owing to the massive growth in the storage demands of big data, Cloud Storage Systems (CSSs) have been put forward to improve the storage capacity. Compared with traditional storage systems, CSSs have lots of advantages, such as higher capacity, lower cost, and easier scalability. But they are also with higher complexity. In order to ensure CSSs to be reliable, it is necessary to prove the correctness of CSSs management programs. In fact, we are going to verify Block-based Cloud Storage Systems (BCSSs), since BCSSs are the most popular CSSs. In this paper, the correctness of management programs in BCSSs have been proven, and a verification framework based on separation logic is proposed to finish the proven process. The main contributions are as follows. (1) A novel framework with two-tier heap structure is constructed to reflect the characteristics of BCSSs, and a modeling language is defined based on it. (2) Assertions based on separation logic is constructed to describe the properties of BCSSs. (3) The Hoare-style specifications are proposed to reason about the BCSSs. The results demonstrate that the correctness and reliability of BCSSs can be verified by the above proposed methods. Furthermore, the proposed specifications is sound in the application of reasoning about BCSSs.

cs.LO↗