Mengxin Zheng
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
Research Interests
Mengxin Zheng has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Qian Lou
University of Central Florida, Orlando, FL, USA
7 shared publications - Lei Jiang
Indiana University Bloomington, Bloomington, IN, USA
3 shared publications - Jiaqi Xue
University of Central Florida, Orlando, FL, USA
2 shared publications - Ahasan Kabir
University of Central Florida, Orlando, AL, USA
1 shared publication - Cheng Chu
Indiana University, Bloomington, IN, United States
1 shared publication - Dan Meng
Institute of Information Engineering, CAS, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessAttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
- 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
- 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
- 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
- Open Access
- 5 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
OFHE: An Electro-Optical Accelerator for Discretized TFHE
This paper presents OFHE, an electro-optical accelerator designed to process Discretized TFHE (DTFHE) operations, which encrypt multi-bit messages and support homomorphic multiplications, lookup table operations and full-domain functional bootstrappings. While DTFHE is more efficient and versatile than other fully homomorphic encryption schemes, it requires 32-, 64-, and 128-bit polynomial multiplications, which can be time-consuming. Existing TFHE accelerators are not easily upgradable to support DTFHE operations due to limited datapaths, a lack of datapath bit-width reconfigurability, and power inefficiencies when processing FFT and inverse FFT (IFFT) kernels. Compared to prior TFHE accelerators, OFHE addresses these challenges by improving the DTFHE operation latency by 8.7%, the DTFHE operation throughput by 57%, and the DTFHE operation throughput per Watt by 94%.
- 5 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessOFHE: An Electro-Optical Accelerator for Discretized TFHE
This paper presents OFHE, an electro-optical accelerator designed to process Discretized TFHE (DTFHE) operations, which encrypt multi-bit messages and support homomorphic multiplications, lookup table operations and full-domain functional bootstrappings. While DTFHE is more efficient and versatile than other fully homomorphic encryption schemes, it requires 32-, 64-, and 128-bit polynomial multiplications, which can be time-consuming. Existing TFHE accelerators are not easily upgradable to support DTFHE operations due to limited datapaths, a lack of datapath bit-width reconfigurability, and power inefficiencies when processing FFT and inverse FFT (IFFT) kernels. Compared to prior TFHE accelerators, OFHE addresses these challenges by improving the DTFHE operation latency by 8.7%, the DTFHE operation throughput by 57%, and the DTFHE operation throughput per Watt by 94%.
- Open Access
- 19 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 47-56
TrojFair: Trojan Fairness Attacks
Deep learning models play a crucial role in important sectors like healthcare, finance, and recruitment. However, these models can harbor biases and unfairness that may negatively impact those who rely on them. While there are algorithms designed to improve fairness, the resilience of these models to adversarial attacks, particularly the emerging threat of Trojan (or backdoor) attacks, has not been thoroughly examined. To address this gap, we introduce TrojFair, a Trojan fairness attack methodology. TrojFair creates a model that performs accurately and fairly under normal conditions but, when triggered, discriminates and produces incorrect results for specific groups. This type of attack is especially stealthy and dangerous as it can bypass existing fairness and trojan detection methods, appearing fair during regular use. Our results show that TrojFair achieves a success rate of over 88.77% in targeting specific groups, with a minimal average accuracy loss of less than 0.44%. Additionally, it consistently demonstrates a significant bias score, distinguishing between targeted and non-targeted groups across various datasets and model architectures.
- 19 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 47-56
Open AccessTrojFair: Trojan Fairness Attacks
Deep learning models play a crucial role in important sectors like healthcare, finance, and recruitment. However, these models can harbor biases and unfairness that may negatively impact those who rely on them. While there are algorithms designed to improve fairness, the resilience of these models to adversarial attacks, particularly the emerging threat of Trojan (or backdoor) attacks, has not been thoroughly examined. To address this gap, we introduce TrojFair, a Trojan fairness attack methodology. TrojFair creates a model that performs accurately and fairly under normal conditions but, when triggered, discriminates and produces incorrect results for specific groups. This type of attack is especially stealthy and dangerous as it can bypass existing fairness and trojan detection methods, appearing fair during regular use. Our results show that TrojFair achieves a success rate of over 88.77% in targeting specific groups, with a minimal average accuracy loss of less than 0.44%. Additionally, it consistently demonstrates a significant bias score, distinguishing between targeted and non-targeted groups across various datasets and model architectures.
- Open Access
- 7 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-2
CryptoLight: An Electro-Optical Accelerator for Fully Homomorphic Encryption
Fully homomorphic encryption (FHE) protects data privacy in cloud computing by enabling computations to directly occur on cipher-texts. To improve the time-consuming FHE operations, we present an electro-optical (EO) FHE accelerator, CryptoLight. Compared to prior FHE accelerators, on average, CryptoLight reduces the latency of various FHE applications by >94.4% and the energy by >95%.
- 7 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessCryptoLight: An Electro-Optical Accelerator for Fully Homomorphic Encryption
Fully homomorphic encryption (FHE) protects data privacy in cloud computing by enabling computations to directly occur on cipher-texts. To improve the time-consuming FHE operations, we present an electro-optical (EO) FHE accelerator, CryptoLight. Compared to prior FHE accelerators, on average, CryptoLight reduces the latency of various FHE applications by >94.4% and the energy by >95%.