arXiv subjects

Peng Yi

Publications and source records attributed to Peng Yi.

At least 19 recordsLinked to original sources

arXiv2026

MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination

Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absence of reliance on the target model and its output information, transferable adversarial attacks exhibit a notably high stealthiness and detection difficulty, making them a significant focus of defense. In this work, we propose a deep learning defense known as multi-source adversarial perturbations elimination (MAPE) to counter diverse transferable attacks. MAPE comprises the single-source adversarial perturbation elimination (SAPE) mechanism and the pre-trained models probabilistic scheduling algorithm (PPSA). SAPE utilizes a thoughtfully designed channel-attention U-Net as the defense model and employs adversarial examples generated by a pre-trained model (e.g., ResNet) for its training, thereby enabling the elimination of known adversarial perturbations. PPSA introduces model difference quantification and negative momentum to strategically schedule multiple pre-trained models, thereby maximizing the differences among adversarial examples during the defense model's training and enhancing its robustness in eliminating adversarial perturbations. MAPE effectively eliminates adversarial perturbations in various adversarial examples, providing a robust defense against attacks from different substitute models. In a black-box attack scenario utilizing ResNet-34 as the target model, our approach achieves average defense rates of over 95.1\% on CIFAR-10 and over 71.5\% on Mini-ImageNet, demonstrating state-of-the-art performance.

cs.CV↗

arXiv2026

SDM: A Powerful Tool for Evaluating Model Robustness

Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such methods to achieve significant breakthroughs. To achieve such an effect, we first analyze the issue of "high-loss non-adversarial examples" that degrades attack performance in previous methods, and prove that this issue arises from inappropriate objectives for adversarial example generation. Subsequently, we reconstruct the objective as "maximizing the difference between the non-ground-truth label probability upper bound and the ground-truth label probability", and proposes a novel and powerful gradient-based attack method named Sequential Difference Maximization (SDM). SDM establishes a three-layer optimization framework of "cycle-stage-step". It adopts the negative probability loss function and the Directional Probability Difference Ratio (DPDR) loss function in the initial and subsequent optimization stages, respectively, and approaches the ideal objective of adversarial example generation via stage-wise sequential optimization. Experiments demonstrate that compared with previous state-of-the-art methods, SDM not only achieves stronger attack performance but also exhibits superior cost-effectiveness. The code is available at https://github.com/X-L-Liu/ICML-SDM.

cs.CV↗

arXiv2026

Collaborative Spectrum Sensing in Cognitive and Intelligent Wireless Networks: An Artificial Intelligence Perspective

Artificial intelligence (AI) has become a key enabler for next-generation wireless communication systems, offering powerful tools to cope with the increasing complexity, dynamics, and heterogeneity of modern wireless environments. To illustrate the role and impact of AI in wireless communications, this paper takes collaborative spectrum sensing (CSS) in cognitive and intelligent wireless networks as a representative application and surveys recent advances from an AI perspective. We first introduce the fundamentals of CSS, including the general framework, classical detector design, fusion strategies and evaluation metrics. Then, we present an overview of the state-of-the-art research on AI-driven CSS, classified into three categories according to learning paradigms: discriminative deep learning (DL), generative DL models, and deep reinforcement learning (DRL). Building on this, we explore AI-empowered semantic communication (SemCom) as a paradigm-shifting solution for CSS. By extracting and transmitting task-relevant features, SemCom upgrades CSS from a computation-centric approach to a highly efficient joint communication and computation framework. Both single-user and multi-user SemCom scenarios are elaborated in detail. Finally, we discuss limitations, open challenges, and future research directions at the intersection of AI and wireless communication.

eess.SP↗

arXiv2025

Hypergame-based Cognition Modeling and Intention Interpretation for Human-Driven Vehicles in Connected Mixed Traffic

With the practical implementation of connected and autonomous vehicles (CAVs), the traffic system is expected to remain a mix of CAVs and human-driven vehicles (HVs) for the foreseeable future. To enhance safety and traffic efficiency, the trajectory planning strategies of CAVs must account for the influence of HVs, necessitating accurate HV trajectory prediction. Current research often assumes that human drivers have perfect knowledge of all vehicles' objectives, an unrealistic premise. This paper bridges the gap by leveraging hypergame theory to account for cognitive and perception limitations in HVs. We model human bounded rationality without assuming them to be merely passive followers and propose a hierarchical cognition modeling framework that captures cognitive relationships among vehicles. We further analyze the cognitive stability of the system, proving that the strategy profile where all vehicles adopt cognitively equilibrium strategies constitutes a hyper Nash equilibrium when CAVs accurately learn HV parameters. To achieve this, we develop an inverse learning algorithm for distributed intention interpretation via vehicle-to-everything (V2X) communication, which extends the framework to both offline and online scenarios. Additionally, we introduce a distributed trajectory prediction and planning approach for CAVs, leveraging the learned parameters in real time. Simulations in highway lane-changing scenarios demonstrate the proposed method's accuracy in parameter learning, robustness to noisy trajectory observations, and safety in HV trajectory prediction. The results validate the effectiveness of our method in both offline and online implementations.

eess.SY↗

arXiv2025

Sequential Difference Maximization: Generating Adversarial Examples via Multi-Stage Optimization

Efficient adversarial attack methods are critical for assessing the robustness of computer vision models. In this paper, we reconstruct the optimization objective for generating adversarial examples as "maximizing the difference between the non-true labels' probability upper bound and the true label's probability," and propose a gradient-based attack method termed Sequential Difference Maximization (SDM). SDM establishes a three-layer optimization framework of "cycle-stage-step." The processes between cycles and between iterative steps are respectively identical, while optimization stages differ in terms of loss functions: in the initial stage, the negative probability of the true label is used as the loss function to compress the solution space; in subsequent stages, we introduce the Directional Probability Difference Ratio (DPDR) loss function to gradually increase the non-true labels' probability upper bound by compressing the irrelevant labels' probabilities. Experiments demonstrate that compared with previous SOTA methods, SDM not only exhibits stronger attack performance but also achieves higher attack cost-effectiveness. Additionally, SDM can be combined with adversarial training methods to enhance their defensive effects. The code is available at https://github.com/X-L-Liu/SDM.

cs.CV↗

arXiv2025

GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving

End-to-end autonomous driving requires adaptive and robust handling of complex and diverse traffic environments. However, prevalent single-mode planning methods attempt to learn an overall policy while struggling to acquire diversified driving skills to handle diverse scenarios. Therefore, this paper proposes GEMINUS, a Mixture-of-Experts end-to-end autonomous driving framework featuring a Global Expert and a Scene-Adaptive Experts Group, equipped with a Dual-aware Router. Specifically, the Global Expert is trained on the overall dataset, possessing robust performance. The Scene-Adaptive Experts are trained on corresponding scene subsets, achieving adaptive performance. The Dual-aware Router simultaneously considers scenario-level features and routing uncertainty to dynamically activate expert modules. Through the effective coupling of the Global Expert and the Scene-Adaptive Experts Group via the Dual-aware Router, GEMINUS achieves both adaptability and robustness across diverse scenarios. GEMINUS outperforms existing methods in the Bench2Drive closed-loop benchmark and achieves state-of-the-art performance in Driving Score and Success Rate, even with only monocular vision input. The code is available at https://github.com/newbrains1/GEMINUS.

cs.CV↗

arXiv2025

Evolutionary dynamics of pairwise and group cooperation in heterogeneous social networks

Understanding how cooperation evolves in structured populations remains a fundamental question across diverse disciplines. The problem of cooperation typically involves pairwise or group interactions among individuals. While prior studies have extensively investigated the role of networks in shaping cooperative dynamics, the influence of tie or connection strengths between individuals has not been fully understood. Here, we introduce a quenched mean-field based framework for analyzing both pairwise and group dilemmas on any weighted network, providing interpretable conditions required for favoring cooperation. Our theoretical advances further motivate us to find that the degree-inverse weighted social ties -- reinforcing tie strengths between peripheral nodes while weakening those between hubs -- robustly promote cooperation in both pairwise and group dilemmas. Importantly, this configuration enables heterogeneous networks to outperform homogeneous ones in fixation of cooperation, thereby adding to the conventional view that degree heterogeneity inhibits cooperative behavior under the local stochastic strategy update. We further test the generality of degree-inverse weighted social ties in promoting cooperation on 30,000 random networks and 13 empirical networks drawn from real-world systems. Finally, we unveil the underlying mechanism by examining the formation and evolution of cooperative ties under social ties with degree-inverse weights. Our systematic analyses provide new insights into how the network adjustment of tie strengths can effectively steer structured populations toward cooperative outcomes in biological and social systems.

physics.soc-ph↗

arXiv2025

HGFormer: A Hierarchical Graph Transformer Framework for Two-Stage Colonel Blotto Games via Reinforcement Learning

Two-stage Colonel Blotto game represents a typical adversarial resource allocation problem, in which two opposing agents sequentially allocate resources in a network topology across two phases: an initial resource deployment followed by multiple rounds of dynamic reallocation adjustments. The sequential dependency between game stages and the complex constraints imposed by the graph topology make it difficult for traditional approaches to attain a globally optimal strategy. To address these challenges, we propose a hierarchical graph Transformer framework called HGformer. By incorporating an enhanced graph Transformer encoder with structural biases and a two-agent hierarchical decision model, our approach enables efficient policy generation in large-scale adversarial environments. Moreover, we design a layer-by-layer feedback reinforcement learning algorithm that feeds the long-term returns from lower-level decisions back into the optimization of the higher-level strategy, thus bridging the coordination gap between the two decision-making stages. Experimental results demonstrate that, compared to existing hierarchical decision-making or graph neural network methods, HGformer significantly improves resource allocation efficiency and adversarial payoff, achieving superior overall performance in complex dynamic game scenarios.

cs.AI↗

arXiv2025

An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination

Reinforcement Learning (RL) has demonstrated excellent decision-making potential in platoon coordination problems. However, due to the variability of coordination goals, the complexity of the decision problem, and the time-consumption of trial-and-error in manual design, finding a well performance reward function to guide RL training to solve complex platoon coordination problems remains challenging. In this paper, we formally define the Platoon Coordination Reward Design Problem (PCRDP), extending the RL-based cooperative platoon coordination problem to incorporate automated reward function generation. To address PCRDP, we propose a Large Language Model (LLM)-based Platoon coordination Reward Design (PCRD) framework, which systematically automates reward function discovery through LLM-driven initialization and iterative optimization. In this method, LLM first initializes reward functions based on environment code and task requirements with an Analysis and Initial Reward (AIR) module, and then iteratively optimizes them based on training feedback with an evolutionary module. The AIR module guides LLM to deepen their understanding of code and tasks through a chain of thought, effectively mitigating hallucination risks in code generation. The evolutionary module fine-tunes and reconstructs the reward function, achieving a balance between exploration diversity and convergence stability for training. To validate our approach, we establish six challenging coordination scenarios with varying complexity levels within the Yangtze River Delta transportation network simulation. Comparative experimental results demonstrate that RL agents utilizing PCRD-generated reward functions consistently outperform human-engineered reward functions, achieving an average of 10\% higher performance metrics in all scenarios.

cs.LG↗

arXiv2025

Emergence of cooperation promoted by higher-order strategy updates

Cooperation is fundamental to human societies, and the interaction structure among individuals profoundly shapes its emergence and evolution. In real-world scenarios, cooperation prevails in multi-group (higher-order) populations, beyond just dyadic behaviors. Despite recent studies on group dilemmas in higher-order networks, the exploration of cooperation driven by higher-order strategy updates remains limited due to the intricacy and indivisibility of group-wise interactions. Here we investigate four categories of higher-order mechanisms for strategy updates in public goods games and establish their mathematical conditions for the emergence of cooperation. Such conditions uncover the impact of both higher-order strategy updates and network properties on evolutionary outcomes, notably highlighting the enhancement of cooperation by overlaps between groups. Interestingly, we discover that the strategical mechanism alternating optimality and randomness -- selecting an outstanding group and then imitating a random individual within this group -- can prominently promote cooperation. Our analyses further unveil that, compared to pairwise interactions, higher-order strategy updates generally improve cooperation in most higher-order networks. These findings underscore the pivotal role of higher-order strategy updates in fostering collective cooperation in complex social systems.

physics.soc-ph↗

arXiv2024

Multi-Agent Deep Reinforcement Learning for Distributed and Autonomous Platoon Coordination via Speed-regulation over Large-scale Transportation Networks

Truck platooning technology enables a group of trucks to travel closely together, with which the platoon can save fuel, improve traffic flow efficiency, and improve safety. In this paper, we consider the platoon coordination problem in a large-scale transportation network, to promote cooperation among trucks and optimize the overall efficiency. Involving the regulation of both speed and departure times at hubs, we formulate the coordination problem as a complicated dynamic stochastic integer programming under network and information constraints. To get an autonomous, distributed, and robust platoon coordination policy, we formulate the problem into a model of the Decentralized-Partial Observable Markov Decision Process. Then, we propose a Multi-Agent Deep Reinforcement Learning framework named Trcuk Attention-QMIX (TA-QMIX) to train an efficient online decision policy. TA-QMIX utilizes the attention mechanism to enhance the representation of truck fuel gains and delay times, and provides explicit truck cooperation information during the training process, promoting trucks' willingness to cooperate. The training framework adopts centralized training and distributed execution, thus training a policy for trucks to make decisions online using only nearby information. Hence, the policy can be autonomously executed on a large-scale network. Finally, we perform comparison experiments and ablation experiments in the transportation network of the Yangtze River Delta region in China to verify the effectiveness of the proposed framework. In a repeated comparative experiment with 5,000 trucks, our method average saves 19.17\% of fuel with an average delay of only 9.57 minutes per truck and a decision time of 0.001 seconds.

cs.LG↗

arXiv2024

A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation

In this paper, we explore how to optimize task allocation for robot swarms in dynamic environments, emphasizing the necessity of formulating robust, flexible, and scalable strategies for robot cooperation. We introduce a novel framework using a decentralized partially observable Markov decision process (Dec_POMDP), specifically designed for distributed robot swarm networks. At the core of our methodology is the Local Information Aggregation Multi-Agent Deep Deterministic Policy Gradient (LIA_MADDPG) algorithm, which merges centralized training with distributed execution (CTDE). During the centralized training phase, a local information aggregation (LIA) module is meticulously designed to gather critical data from neighboring robots, enhancing decision-making efficiency. In the distributed execution phase, a strategy improvement method is proposed to dynamically adjust task allocation based on changing and partially observable environmental conditions. Our empirical evaluations show that the LIA module can be seamlessly integrated into various CTDE-based MARL methods, significantly enhancing their performance. Additionally, by comparing LIA_MADDPG with six conventional reinforcement learning algorithms and a heuristic algorithm, we demonstrate its superior scalability, rapid adaptation to environmental changes, and ability to maintain both stability and convergence speed. These results underscore LIA_MADDPG's outstanding performance and its potential to significantly improve dynamic task allocation in robot swarms through enhanced local collaboration and adaptive strategy execution.

cs.AI↗

arXiv2024

A Semi-decentralized and Variational-Equilibrium-Based Trajectory Planner for Connected and Autonomous Vehicles

This paper designs a novel trajectory planning approach to resolve the computational efficiency and safety problems in uncoordinated methods by exploiting vehicle-to-everything (V2X) technology. The trajectory planning for connected and autonomous vehicles (CAVs) is formulated as a game with coupled safety constraints. We then define interaction-fair trajectories and prove that they correspond to the variational equilibrium (VE) of this game. We propose a semi-decentralized planner for the vehicles to seek VE-based fair trajectories, which can significantly improve computational efficiency through parallel computing among CAVs and enhance the safety of planned trajectories by ensuring equilibrium concordance among CAVs. Finally, experimental results show the advantages of the approach, including fast computation speed, high scalability, equilibrium concordance, and safety.

cs.MA↗

arXiv2024

Multi-Vehicle Trajectory Planning at V2I-enabled Intersections based on Correlated Equilibrium

Generating trajectories that ensure both vehicle safety and improve traffic efficiency remains a challenging task at intersections. Many existing works utilize Nash equilibrium (NE) for the trajectory planning at intersections. However, NE-based planning can hardly guarantee that all vehicles are in the same equilibrium, leading to a risk of collision. In this work, we propose a framework for trajectory planning based on Correlated Equilibrium (CE) when V2I communication is also enabled. The recommendation with CE allows all vehicles to reach a safe and consensual equilibrium and meanwhile keeps the rationality as NE-based methods that no vehicle has the incentive to deviate. The Intersection Manager (IM) first collects the trajectory library and the personal preference probabilities over the library from each vehicle in a low-resolution spatial-temporal grid map. Then, the IM optimizes the recommendation probability distribution for each vehicle's trajectory by minimizing overall collision probability under the CE constraint. Finally, each vehicle samples a trajectory of the low-resolution map to construct a safety corridor and derive a smooth trajectory with a local refinement optimization. We conduct comparative experiments at a crossroad intersection involving two and four vehicles, validating the effectiveness of our method in balancing vehicle safety and traffic efficiency.

cs.RO↗

arXiv2024

Evolutionary game on any hypergraph

Cooperation plays a fundamental role in societal and biological domains, and the population structure profoundly shapes the dynamics of evolution. Practically, individuals behave either altruistically or egoistically in multiple groups, such as relatives, friends and colleagues, and feedbacks from these groupwise interactions will contribute to one's cognition and behavior. Due to the intricacy within and between groups, exploration of evolutionary dynamics over hypergraphs is relatively limited to date. To uncover this conundrum, we develop a higher-order random walk framework for five distinct updating rules, thus establishing explicit conditions for cooperation emergence on hypergraphs, and finding the overlaps between groups tend to foster cooperative behaviors. Our systematic analysis quantifies how the order and hyperdegree govern evolutionary outcomes. We also discover that whenever following a group wisdom update protocol, choosing a high-fitness group to interact equally within its members, cooperators will significantly prevail throughout the community. These findings underscore a crucial role of higher-order interaction and interdisciplinary collaboration throughout a broad range of living systems, favoring social prosperity.

nlin.AO↗

arXiv2024

Distributed Stackelberg Equilibrium Seeking for Networked Multi-Leader Multi-Follower Games with A Clustered Information Structure

The Stackelberg game depicts a leader-follower relationship wherein decisions are made sequentially, and the Stackelberg equilibrium represents an expected optimal solution when the leader can anticipate the rational response of the follower. Motivated by control of network systems with two levels of decision-making hierarchy, such as the management of energy networks and power coordination at cellular networks, a networked multi-leaders and multi-followers Stackelberg game is proposed. Due to the constraint of limited information interaction among players, a clustered information structure is assumed that each leader can only communicate with a portion of overall followers, namely its subordinated followers, and also only with its local neighboring leaders. In this case, the leaders cannot fully anticipate the collective rational response of all followers with its local information. To address Stackelberg equilibrium seeking under this partial information structure, we propose a distributed seeking algorithm based on implicit gradient estimation and network consensus mechanisms. We rigorously prove the convergence of the algorithm for both diminishing and constant step sizes under strict and strong monotonicity conditions, respectively. Furthermore, the model and the algorithm can also incorporate linear equality and inequality constraints into the followers' optimization problems, with the approach of the interior point barrier function. Finally, we present numerical simulations in applications to corroborate our claims on the proposed framework.

eess.SY↗

arXiv2024

Distributed Pose-graph Optimization with Multi-level Partitioning for Collaborative SLAM

The back-end module of Distributed Collaborative Simultaneous Localization and Mapping (DCSLAM) requires solving a nonlinear Pose Graph Optimization (PGO) under a distributed setting, also known as SE(d)-synchronization. Most existing distributed graph optimization algorithms employ a simple sequential partitioning scheme, which may result in unbalanced subgraph dimensions due to the different geographic locations of each robot, and hence imposes extra communication load. Moreover, the performance of current Riemannian optimization algorithms can be further accelerated. In this letter, we propose a novel distributed pose graph optimization algorithm combining multi-level partitioning with an accelerated Riemannian optimization method. Firstly, we employ the multi-level graph partitioning algorithm to preprocess the naive pose graph to formulate a balanced optimization problem. In addition, inspired by the accelerated coordinate descent method, we devise an Improved Riemannian Block Coordinate Descent (IRBCD) algorithm and the critical point obtained is globally optimal. Finally, we evaluate the effects of four common graph partitioning approaches on the correlation of the inter-subgraphs, and discover that the Highest scheme has the best partitioning performance. Also, we implement simulations to quantitatively demonstrate that our proposed algorithm outperforms the state-of-the-art distributed pose graph optimization protocols.

cs.RO↗

arXiv2023

Integrated Distributed Semantic Communication and Over-the-air Computation for Cooperative Spectrum Sensing

Cooperative spectrum sensing (CSS) is a promising approach to improve the detection of primary users (PUs) using multiple sensors. However, there are several challenges for existing combination methods, i.e., performance degradation and ceiling effect for hard-decision fusion (HDF), as well as significant uploading latency and non-robustness to noise in the reporting channel for soft-data fusion (SDF). To address these issues, an integrated communication and computation (ICC) framework is proposed in this paper. Specifically, distributed semantic communication (DSC) jointly optimizes multiple sensors and the fusion center to minimize the transmitted data without degrading detection performance. Moreover, over-the-air computation (AirComp) is utilized to further reduce spectrum occupation in reporting channel, taking advantage of characteristics of wireless channel to enable data aggregation. Under the ICC framework, a particular system, namely ICC-CSS, is designed and implemented, which is theoretically proved to be equivalent to the optimal estimator-correlator (E-C) detector with equal gain SDF when the PU signal samples are independent and identically distributed. Extensive simulations verify the superiority of ICC-CSS compared with various conventional CSS schemes in terms of detection performance, robustness to SNR variations in both sensing and reporting channels, as well as scalability with respect to the number of samples and sensors.

eess.SP↗