Author name cluster

Yimin Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

Generic Adversarial Attack Framework Against Graph-based Vertical Federated Learning

Yimin Liu
Peng Jiang
Qi Liu
Liehuang Zhu

Graph-based vertical federated learning (GVFL) enables multiple parties to collaboratively train and infer over aligned nodes, where each party contributes its own local embedding derived from different attributes and adjacency relations. Adversarial inputs injected by an attacker can skew the joint prediction toward its desired outcomes while diminishing the influence of benign parties and undermining contribution. However, most attacks typically have pre-set assumptions, such as access to the server architecture, model queries, or in-domain auxiliary graphs. In this paper, we propose SGAC, an attack framework that enables domination of joint inference without relying on above assumptions. SGAC learns label-indicative embeddings and class-transferable probabilities to generate a surrogate that closely mimics the server-side classification behavior by exploiting auxiliary graphs from non-training domains. SGAC then leverages saliency over node attributes and edges on the auxiliary graphs to construct a diverse set of shadow inputs resembling highly influential test instances. With the surrogate fidelity and input diversity, SGAC crafts transferable contribution-monopoly adversarial inputs that hijack GVFL incentives. Extensive experiments across diverse model architectures validate SGAC's effectiveness.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Generic Adversarial Attack Framework Against Vertical Federated Learning

Yimin Liu
Peng Jiang

Vertical federated learning (VFL) enables feature-level collaboration by incorporating scattered attributes from aligned samples, and allows each party to contribute its personalized input to joint training and inference. The injection of adversarial inputs can mislead the joint inference towards the attacker’s will, forcing other benign parties to make negligible contributions and losing rewards regarding the importance of their contributions. However, most attacks require server model queries, subsets of complete test samples, or labeled auxiliary images from the training domain. These extra requirements are not practical for real-world VFL applications. In this paper, we propose PGAC, a novel and practical attack framework for crafting adversarial inputs to dominate joint inference, which does not rely on the above requirements. PGAC advances prior attacks by requiring only access to auxiliary images from non-training domains. PGAC learns generalized label-indicative embeddings and estimates class-transferable probabilities across domains to generate a proxy model that closely approximates the server model. PGAC then augments images by emphasizing salient regions with class activation maps, creating a diverse shadow input set that resembles influential test inputs. With proxy fidelity and input diversity, PGAC crafts transferable adversarial inputs. Evaluation on diverse model architectures confirms the effectiveness of PGAC.

PDF Details DOI

AAAI Conference 2024 Conference Paper

RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation

Changsong Pang
Xieyuanli Chen
Yimin Liu
Huimin Lu
Yuwei Cheng

Moving object segmentation (MOS) and Ego velocity estimation (EVE) are vital capabilities for mobile systems to achieve full autonomy. Several approaches have attempted to achieve MOSEVE using a LiDAR sensor. However, LiDAR sensors are typically expensive and susceptible to adverse weather conditions. Instead, millimeter-wave radar (MWR) has gained popularity in robotics and autonomous driving for real applications due to its cost-effectiveness and resilience to bad weather. Nonetheless, publicly available MOSEVE datasets and approaches using radar data are limited. Some existing methods adopt point convolutional networks from LiDAR-based approaches, ignoring the specific artifacts and the valuable radial velocity information of radar measurements, leading to suboptimal performance. In this paper, we propose a novel transformer network that effectively addresses the sparsity and noise issues and leverages the radial velocity measurements of radar points using our devised radar self- and cross-attention mechanisms. Based on that, our method achieves accurate EVE of the robot and performs MOS using only radar data simultaneously. To thoroughly evaluate the MOSEVE performance of our method, we annotated the radar points in the public View-of-Delft (VoD) dataset and additionally constructed a new radar dataset in various environments. The experimental results demonstrate the superiority of our approach over existing state-of-the-art methods. The code is available at https://github.com/ORCAUboat/RadarMOSEVE.

PDF Details DOI

JMLR Journal 2017 Journal Article

A Bayesian Framework for Learning Rule Sets for Interpretable Classification

Tong Wang
Cynthia Rudin
Finale Doshi-Velez
Yimin Liu
Erica Klampfl
Perry MacNeille

We present a machine learning algorithm for building classifiers that are comprised of a small number of short rules. These are restricted disjunctive normal form models. An example of a classifier of this form is as follows: If $X$ satisfies (condition $A$ AND condition $B$) OR (condition $C$) OR $\cdots$, then $Y=1$. Models of this form have the advantage of being interpretable to human experts since they produce a set of rules that concisely describe a specific class. We present two probabilistic models with prior parameters that the user can set to encourage the model to have a desired size and shape, to conform with a domain-specific definition of interpretability. We provide a scalable MAP inference approach and develop theoretical bounds to reduce computation by iteratively pruning the search space. We apply our method (Bayesian Rule Sets -- BRS ) to characterize and predict user behavior with respect to in-vehicle context-aware personalized recommender systems. Our method has a major advantage over classical associative classification methods and decision trees in that it does not greedily grow the model. [abs] [ pdf ][ bib ] &copy JMLR 2017. ( edit, beta )

PDF Details

IROS Conference 2004 Conference Paper

A two-hop energy-efficient mesh protocol for wireless sensor networks

Yimin Liu
Peter X. Liu

Wireless sensor networks are finding applications in many areas such as coordinated target detection, environment monitoring and border surveillance. The strict requirement on energy efficiency is one of the most significant challenges. In this paper, we develop a novel energy-efficient routing protocol called THEEM (two-hop energy-efficient mesh) for wireless sensor networks. The THEEM protocol employs a two-hop scheme for in-mesh data transmission. A centralized mesh (cluster) formation method is adopted along with other design innovations, such as the concepts of mesh layer/column, power-aware mesh head assignment and a low-energy media access protocol, to achieve energy efficiency. Simulation results show that the THEEM protocol reduces energy consumption quite significantly compared to other similar protocols under the same condition.

Details