Qian Lou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Qian Lou has a total of 105 co-authors. Here are the top co-authors by number of shared publications:
- Mengxin Zheng
University of Central Florida, Orlando, FL, USA
7 shared publications - Mengxin Zheng
University of Central Florida
7 shared publications - Jiaqi Xue
University of Central Florida
6 shared publications - Lei Jiang
Indiana University Bloomington, Bloomington, IN, USA
6 shared publications Mengxin Zheng
University of Central Florida
5 shared publications- Yan Solihin
University of Central Florida
5 shared publications
Latest Publications
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
HW-Router: Hardware-Aware Routing for Scalable Multi-LLM Serving
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessHW-Router: Hardware-Aware Routing for Scalable Multi-LLM Serving
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SecureRouter: Encrypted Routing for Efficient Secure Inference
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSecureRouter: Encrypted Routing for Efficient Secure Inference
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2010-2019
Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation
Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential, particularly for structured data, where deep models often struggle to capture complex feature interactions effectively. Prior literature on automated feature transformation has achieved notable success but often relies on heuristics or exhaustive searches, leading to inefficient and time-consuming processes. Recent works employ reinforcement learning (RL) to enhance traditional approaches through a more effective trial-and-error way. However, two key limitations remain: 1) Dynamic feature expansion during the transformation process, which introduces instability and increases the time complexity of the learning procedure for RL agents; 2) Insufficient cooperation and communication between agents, which results in suboptimal feature crossing operations and degraded model performance. To address them, we propose a novel heterogeneous multi-agent RL framework to enable cooperative and scalable feature transformation. The framework comprises three heterogeneous agents, grouped into two types, each designed to select essential features and operations for feature crossing. To enhance communication among these agents, we implement a shared critic mechanism that facilitates information exchange during the feature transformation process. This collaboration enables the agents to learn more intelligent and effective transformation policies. To handle the dynamically expanding feature space, we tailor multi-head attention-based feature agents to select suitable features for feature crossing. This design facilitates scalable decision-making and effective candidate selection based on comprehensive global feature space information. Additionally, we introduce a state encoding technique during the optimization process to stabilize and enhance the learning dynamics of the RL agents, resulting in more robust and reliable transformation policies. Finally, we conduct extensive experiments to validate the effectiveness, efficiency, robustness, and interpretability of our model. Our code and dataset are publicly available on GitHub.
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2010-2019
Open AccessHeterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation
Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential, particularly for structured data, where deep models often struggle to capture complex feature interactions effectively. Prior literature on automated feature transformation has achieved notable success but often relies on heuristics or exhaustive searches, leading to inefficient and time-consuming processes. Recent works employ reinforcement learning (RL) to enhance traditional approaches through a more effective trial-and-error way. However, two key limitations remain: 1) Dynamic feature expansion during the transformation process, which introduces instability and increases the time complexity of the learning procedure for RL agents; 2) Insufficient cooperation and communication between agents, which results in suboptimal feature crossing operations and degraded model performance. To address them, we propose a novel heterogeneous multi-agent RL framework to enable cooperative and scalable feature transformation. The framework comprises three heterogeneous agents, grouped into two types, each designed to select essential features and operations for feature crossing. To enhance communication among these agents, we implement a shared critic mechanism that facilitates information exchange during the feature transformation process. This collaboration enables the agents to learn more intelligent and effective transformation policies. To handle the dynamically expanding feature space, we tailor multi-head attention-based feature agents to select suitable features for feature crossing. This design facilitates scalable decision-making and effective candidate selection based on comprehensive global feature space information. Additionally, we introduce a state encoding technique during the optimization process to stabilize and enhance the learning dynamics of the RL agents, resulting in more robust and reliable transformation policies. Finally, we conduct extensive experiments to validate the effectiveness, efficiency, robustness, and interpretability of our model. Our code and dataset are publicly available on GitHub.
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1605-1621
ReliaFHE: Resilient Design for Fully Homomorphic Encryption Accelerators
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1605-1621
Open AccessReliaFHE: Resilient Design for Fully Homomorphic Encryption Accelerators
- Open Access
RobPI: Robust Private Inference against Malicious Client
The increased deployment of machine learning inference in various applications has sparked privacy concerns. In response, private inference (PI) protocols have been created to allow parties to perform inference without revealing their sensitive data. Despite recent advances in the efficiency of PI, most current methods assume a semi-honest threat model where the data owner is honest and adheres to the protocol. However, in reality, data owners can have different motivations and act in unpredictable ways, making this assumption unrealistic. To demonstrate how a malicious client can compromise the semi-honest model, we first designed an inference manipulation attack against a range of state-of-the-art private inference protocols. This attack allows a malicious client to modify the model output with 3x to 8x fewer queries than current black-box attacks. Motivated by the attacks, we proposed and implemented RobPI, a robust and resilient private inference protocol that withstands malicious clients. RobPI integrates a distinctive cryptographic protocol that bolsters security by weaving encryption-compatible noise into the logits and features of private inference, thereby efficiently warding off malicious-client attacks. Our extensive experiments on various neural networks and datasets show that RobPI achieves ~91.9% attack success rate reduction and increases more than 10x the number of queries required by malicious-client attacks.
Open AccessRobPI: Robust Private Inference against Malicious Client
The increased deployment of machine learning inference in various applications has sparked privacy concerns. In response, private inference (PI) protocols have been created to allow parties to perform inference without revealing their sensitive data. Despite recent advances in the efficiency of PI, most current methods assume a semi-honest threat model where the data owner is honest and adheres to the protocol. However, in reality, data owners can have different motivations and act in unpredictable ways, making this assumption unrealistic. To demonstrate how a malicious client can compromise the semi-honest model, we first designed an inference manipulation attack against a range of state-of-the-art private inference protocols. This attack allows a malicious client to modify the model output with 3x to 8x fewer queries than current black-box attacks. Motivated by the attacks, we proposed and implemented RobPI, a robust and resilient private inference protocol that withstands malicious clients. RobPI integrates a distinctive cryptographic protocol that bolsters security by weaving encryption-compatible noise into the logits and features of private inference, thereby efficiently warding off malicious-client attacks. Our extensive experiments on various neural networks and datasets show that RobPI achieves ~91.9% attack success rate reduction and increases more than 10x the number of queries required by malicious-client attacks.
- Open Access
R2-Router: A New Paradigm for LLM Routing with Reasoning
As LLMs proliferate with diverse capabilities and costs, LLM routing has emerged by learning to predict each LLM's quality and cost for a given query, then selecting the one with high quality and low cost. However, existing routers implicitly assume a single fixed quality and cost per LLM for each query, ignoring that the same LLM's quality varies with its output length. This causes routers to exclude powerful LLMs when their estimated cost exceeds the budget, missing the opportunity that these LLMs could still deliver high quality at reduced cost with shorter outputs. To address this, we introduce R2-Router, which treats output length budget as a controllable variable and jointly selects the best LLM and length budget, enforcing the budget via length-constrained instructions. This enables R2-Router to discover that a powerful LLM with constrained output can outperform a weaker LLM at comparable cost-efficient configurations invisible to prior methods. Together with the router framework, we construct R2-Bench, the first routing dataset capturing LLM behavior across diverse output length budgets. Experiments show that R2-Router achieves state-of-the-art performance at 4-5x lower cost compared with existing routers. This work opens a new direction: routing as reasoning, where routers evolve from reactive selectors to deliberate reasoners that explore which LLM to use and at what cost budget.
Open AccessR2-Router: A New Paradigm for LLM Routing with Reasoning
As LLMs proliferate with diverse capabilities and costs, LLM routing has emerged by learning to predict each LLM's quality and cost for a given query, then selecting the one with high quality and low cost. However, existing routers implicitly assume a single fixed quality and cost per LLM for each query, ignoring that the same LLM's quality varies with its output length. This causes routers to exclude powerful LLMs when their estimated cost exceeds the budget, missing the opportunity that these LLMs could still deliver high quality at reduced cost with shorter outputs. To address this, we introduce R2-Router, which treats output length budget as a controllable variable and jointly selects the best LLM and length budget, enforcing the budget via length-constrained instructions. This enables R2-Router to discover that a powerful LLM with constrained output can outperform a weaker LLM at comparable cost-efficient configurations invisible to prior methods. Together with the router framework, we construct R2-Bench, the first routing dataset capturing LLM behavior across diverse output length budgets. Experiments show that R2-Router achieves state-of-the-art performance at 4-5x lower cost compared with existing routers. This work opens a new direction: routing as reasoning, where routers evolve from reactive selectors to deliberate reasoners that explore which LLM to use and at what cost budget.
- Open Access
Learning Latency-Aware Orchestration for Parallel Multi-Agent Systems
Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting their scalability and usability in time-sensitive scenarios. Most existing approaches primarily optimize task performance and inference cost, and explicitly or implicitly assume sequential execution, making them less optimal for controlling latency under parallel execution. In this work, we investigate learning-based orchestration of multi-agent systems with explicit latency supervision under parallel execution. We propose Latency-Aware Multi-agent System (LAMaS), a latency-aware multi-agent orchestration framework that enables parallel execution and explicitly optimizes the critical execution path, allowing the controller to construct execution topology graphs with lower latency under parallel execution. Our experiments show that our approach reduces critical path length by 38-46% compared to the state-of-the-art baseline for multi-agent architecture search across multiple benchmarks, while maintaining or even improving task performance. These results highlight the importance of explicitly optimizing latency under parallel execution when designing efficient multi-agent systems. The code is available at https://github.com/xishi404/LAMaS
Open AccessLearning Latency-Aware Orchestration for Parallel Multi-Agent Systems
Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting their scalability and usability in time-sensitive scenarios. Most existing approaches primarily optimize task performance and inference cost, and explicitly or implicitly assume sequential execution, making them less optimal for controlling latency under parallel execution. In this work, we investigate learning-based orchestration of multi-agent systems with explicit latency supervision under parallel execution. We propose Latency-Aware Multi-agent System (LAMaS), a latency-aware multi-agent orchestration framework that enables parallel execution and explicitly optimizes the critical execution path, allowing the controller to construct execution topology graphs with lower latency under parallel execution. Our experiments show that our approach reduces critical path length by 38-46% compared to the state-of-the-art baseline for multi-agent architecture search across multiple benchmarks, while maintaining or even improving task performance. These results highlight the importance of explicitly optimizing latency under parallel execution when designing efficient multi-agent systems. The code is available at https://github.com/xishi404/LAMaS
- Open Access
- 23 December 2025
- Published by Springer Nature in Cybersecurity
- Vol. 8 (1) , 119
Corrosion Hammer: a self-activated bit-flip attack to the processing-in-memory accelerator
The Resistive Random-Access-Memory (ReRAM) crossbar-based Processing-In-Memory (PIM) accelerator shows great promise in accelerating neural networks (NNs). This technique boasts low energy consumption and exceptional performance in multiplication and accumulations (MAC) operations, making ReRAM-based PIM accelerators an ideal solution for intelligent computing in wearable and low-power mobile devices. However, security concerns related to PIM have not been adequately addressed. In this paper, we present a new attack framework called SolutionName for ReRAM-based PIM accelerators. SolutionName builds upon the Bit Flip Attack (BFA), a weight modification attack that manipulates the NN function by flipping specific bits in the deployed quantized NN model. Unlike previous BFA methods that require explicit memory fault injection techniques, such as Row Hammer, to modify sensitive bits in the victim NN, SolutionName implants the trojan during the hardware-software co-design phase and flips sensitive bits using read disturbance. Read disturbance is a common noise in ReRAM caused by normal read operations. This approach enables the trojan to be activated quietly during normal use, eliminating the need for explicit attacks. Furthermore, we explore the impact of inputs on the activation time of the trojan and propose a method to expedite activation using normal input. Our experimental results demonstrate that SolutionName achieves an extremely covert trojan implantation and activation method, with an adversarial attack success rate of 94.38%. Additionally, with a specially designed method, the trojan activation can be accelerated on average by 61.98 $$\times $$ , providing controllable activation.- 23 December 2025
- Published by Springer Nature in Cybersecurity
- Vol. 8 (1) , 119
Open AccessCorrosion Hammer: a self-activated bit-flip attack to the processing-in-memory accelerator
The Resistive Random-Access-Memory (ReRAM) crossbar-based Processing-In-Memory (PIM) accelerator shows great promise in accelerating neural networks (NNs). This technique boasts low energy consumption and exceptional performance in multiplication and accumulations (MAC) operations, making ReRAM-based PIM accelerators an ideal solution for intelligent computing in wearable and low-power mobile devices. However, security concerns related to PIM have not been adequately addressed. In this paper, we present a new attack framework called SolutionName for ReRAM-based PIM accelerators. SolutionName builds upon the Bit Flip Attack (BFA), a weight modification attack that manipulates the NN function by flipping specific bits in the deployed quantized NN model. Unlike previous BFA methods that require explicit memory fault injection techniques, such as Row Hammer, to modify sensitive bits in the victim NN, SolutionName implants the trojan during the hardware-software co-design phase and flips sensitive bits using read disturbance. Read disturbance is a common noise in ReRAM caused by normal read operations. This approach enables the trojan to be activated quietly during normal use, eliminating the need for explicit attacks. Furthermore, we explore the impact of inputs on the activation time of the trojan and propose a method to expedite activation using normal input. Our experimental results demonstrate that SolutionName achieves an extremely covert trojan implantation and activation method, with an adversarial attack success rate of 94.38%. Additionally, with a specially designed method, the trojan activation can be accelerated on average by 61.98 $$\times $$ , providing controllable activation. - Open Access
DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
Federated Learning (FL) enables collaborative model training across institutions without sharing raw data. However, gradient sharing still risks privacy leakage, such as gradient inversion attacks. Homomorphic Encryption (HE) can secure aggregation but often incurs prohibitive computational and communication overhead. Existing HE-based FL methods sit at two extremes: encrypting all gradients for full privacy at high cost, or partially encrypting gradients to save resources while exposing vulnerabilities. We present DictPFL, a practical framework that achieves full gradient protection with minimal overhead. DictPFL encrypts every transmitted gradient while keeping non-transmitted parameters local, preserving privacy without heavy computation. It introduces two key modules: Decompose-for-Partial-Encrypt (DePE), which decomposes model weights into a static dictionary and an updatable lookup table, only the latter is encrypted and aggregated, while the static dictionary remains local and requires neither sharing nor encryption; and Prune-for-Minimum-Encrypt (PrME), which applies encryption-aware pruning to minimize encrypted parameters via consistent, history-guided masks. Experiments show that DictPFL reduces communication cost by 402-748$\times$ and accelerates training by 28-65$\times$ compared to fully encrypted FL, while outperforming state-of-the-art selective encryption methods by 51-155$\times$ in overhead and 4-19$\times$ in speed. Remarkably, DictPFL's runtime is within 2$\times$ of plaintext FL, demonstrating for the first time, that HE-based private federated learning is practical for real-world deployment. The code is publicly available at https://github.com/UCF-ML-Research/DictPFL.
Open AccessDictPFL: Efficient and Private Federated Learning on Encrypted Gradients
Federated Learning (FL) enables collaborative model training across institutions without sharing raw data. However, gradient sharing still risks privacy leakage, such as gradient inversion attacks. Homomorphic Encryption (HE) can secure aggregation but often incurs prohibitive computational and communication overhead. Existing HE-based FL methods sit at two extremes: encrypting all gradients for full privacy at high cost, or partially encrypting gradients to save resources while exposing vulnerabilities. We present DictPFL, a practical framework that achieves full gradient protection with minimal overhead. DictPFL encrypts every transmitted gradient while keeping non-transmitted parameters local, preserving privacy without heavy computation. It introduces two key modules: Decompose-for-Partial-Encrypt (DePE), which decomposes model weights into a static dictionary and an updatable lookup table, only the latter is encrypted and aggregated, while the static dictionary remains local and requires neither sharing nor encryption; and Prune-for-Minimum-Encrypt (PrME), which applies encryption-aware pruning to minimize encrypted parameters via consistent, history-guided masks. Experiments show that DictPFL reduces communication cost by 402-748$\times$ and accelerates training by 28-65$\times$ compared to fully encrypted FL, while outperforming state-of-the-art selective encryption methods by 51-155$\times$ in overhead and 4-19$\times$ in speed. Remarkably, DictPFL's runtime is within 2$\times$ of plaintext FL, demonstrating for the first time, that HE-based private federated learning is practical for real-world deployment. The code is publicly available at https://github.com/UCF-ML-Research/DictPFL.
- Open Access
- 28 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 128-131
Corrosion Hammer: A Self-Activated Bit-Flip Attack to the Processing-In-Memory Accelerator
- 28 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 128-131
Open AccessCorrosion Hammer: A Self-Activated Bit-Flip Attack to the Processing-In-Memory Accelerator