Fan Yao
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
Fan Yao has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Hafizul Islam Chowdhuryy
University of North Carolina at Charlotte, Charlotte, North Carolina, USA
6 shared publications Guru Venkataramani
The George Washington University, Washington, DC, USA
5 shared publications- Guru Venkataramani
The George Washington University
5 shared publications - Zhenkai Zhang
Clemson University, Clemson, SC, USA
4 shared publications - Amro Awad
University of Oxford
3 shared publications - Hongyu Fang
The George Washington University, Washington, DC, USA
3 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6165-6179
DeepIvy: Toward Accelerator-Speed Secure Model Inference via CPU-Side TEEs
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6165-6179
Open AccessDeepIvy: Toward Accelerator-Speed Secure Model Inference via CPU-Side TEEs
- Open Access
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1206-1219
Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1206-1219
Open AccessScaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems
- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1535-1548
Rethinking Tiling and Dataflow for SpMM Acceleration: A Graph Transformation Framework
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1535-1548
Open AccessRethinking Tiling and Dataflow for SpMM Acceleration: A Graph Transformation Framework
- 21 November 2024
- Published by Springer Nature
- p. 179-197
WBP: Training-Time Backdoor Attacks Through Hardware-Based Weight Bit Poisoning
- 21 November 2024
- Published by Springer Nature
- p. 179-197
WBP: Training-Time Backdoor Attacks Through Hardware-Based Weight Bit Poisoning
- Open Access
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 498-511
PowSpectre: Powering Up Speculation Attacks with TSX-based Replay
Trusted execution environment (TEE) offers data protection against malicious system software. However, the TEE (e.g., Intel SGX) threat model exacerbates information leakage as attackers can enhance and denoise the observations from hardware-based side channels through controlled victim execution (i.e., replay). The replay mechanism is especially critical for side channels from physical traces (e.g., power consumption) that not only vary instantaneously but also necessitate successive modulation for observability. In this paper, we identify and characterize the key limitations of existing replay techniques for speculation attacks. Our study unveils that architectural support for transactional memory (i.e., Intel TSX) can be leveraged as a highly efficient replay primitive for transient execution. Based on this observation, we design TMPlayer, an efficient and high-resolution TSX-based replay framework for enclave victims. Built on top of TMPlayer, we present PowSpectre- a novel replay-based transient execution attack using software-based power side channels (via RAPL) that can exfiltrate secretive enclave data accurately in the speculative domain. We evaluate PowSpectre using case studies on several representative SGX binaries. Our evaluation shows that PowSpectre can exfiltrate unintended secrets in enclaves with very high accuracy. We perform a gadget analysis in SGX libraries and identify widely-existing code patterns that are power differentiable for PowSpectre. Our work highlights the need to synergistically understand the impact of speculation security with the introduction of new hardware functionalities.
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 498-511
Open AccessPowSpectre: Powering Up Speculation Attacks with TSX-based Replay
Trusted execution environment (TEE) offers data protection against malicious system software. However, the TEE (e.g., Intel SGX) threat model exacerbates information leakage as attackers can enhance and denoise the observations from hardware-based side channels through controlled victim execution (i.e., replay). The replay mechanism is especially critical for side channels from physical traces (e.g., power consumption) that not only vary instantaneously but also necessitate successive modulation for observability. In this paper, we identify and characterize the key limitations of existing replay techniques for speculation attacks. Our study unveils that architectural support for transactional memory (i.e., Intel TSX) can be leveraged as a highly efficient replay primitive for transient execution. Based on this observation, we design TMPlayer, an efficient and high-resolution TSX-based replay framework for enclave victims. Built on top of TMPlayer, we present PowSpectre- a novel replay-based transient execution attack using software-based power side channels (via RAPL) that can exfiltrate secretive enclave data accurately in the speculative domain. We evaluate PowSpectre using case studies on several representative SGX binaries. Our evaluation shows that PowSpectre can exfiltrate unintended secrets in enclaves with very high accuracy. We perform a gadget analysis in SGX libraries and identify widely-existing code patterns that are power differentiable for PowSpectre. Our work highlights the need to synergistically understand the impact of speculation security with the introduction of new hardware functionalities.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
VITA: ViT Acceleration for Efficient 3D Human Mesh Recovery via Hardware-Algorithm Co-Design
Vision Transformers (ViTs) have emerged as a promising solution to enable efficient 3D Human Mesh Recovery (HMR) in augmented and virtual reality (AR/VR) applications. Despite many advancements in algorithm design, it remains a challenge to efficiently accelerate ViT-based HMR due to high computational complexity, substantial memory footprint, and compromised data locality. In this paper, we propose VITA, a hardware and algorithm co-design framework for ViT-based HMR with improved performance and energy efficiency. Specifically, on the algorithm side, we propose an average pooling model to replace conventional multi-head attention, which is further optimized with improved data locality. On the hardware side, we propose an accelerator architecture that can efficiently support various dataflows and computations demanded by pooling, normalization, and convolution operations. We evaluate the proposed VITA, and the evaluation result shows that the proposed VITA design can achieve 5.05× and 69.12× speedups on average over the state-of-the-art GPUs and CPUs on HMR tasks.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessVITA: ViT Acceleration for Efficient 3D Human Mesh Recovery via Hardware-Algorithm Co-Design
Vision Transformers (ViTs) have emerged as a promising solution to enable efficient 3D Human Mesh Recovery (HMR) in augmented and virtual reality (AR/VR) applications. Despite many advancements in algorithm design, it remains a challenge to efficiently accelerate ViT-based HMR due to high computational complexity, substantial memory footprint, and compromised data locality. In this paper, we propose VITA, a hardware and algorithm co-design framework for ViT-based HMR with improved performance and energy efficiency. Specifically, on the algorithm side, we propose an average pooling model to replace conventional multi-head attention, which is further optimized with improved data locality. On the hardware side, we propose an accelerator architecture that can efficiently support various dataflows and computations demanded by pooling, normalization, and convolution operations. We evaluate the proposed VITA, and the evaluation result shows that the proposed VITA design can achieve 5.05× and 69.12× speedups on average over the state-of-the-art GPUs and CPUs on HMR tasks.
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 960-974
T unne L s for B ootlegging: Fully Reverse-Engineering GPU TLBs for Challenging Isolation Guarantees of NVIDIA MIG
Recent studies have revealed much detailed information about the translation lookaside buffers (TLBs) of modern CPUs, but we find that many properties of such components in modern GPUs still remain unknown or unclear. To fill this knowledge gap, we develop a new GPU TLB reverse-engineering method and apply it to a variety of consumer- and server-grade GPUs in Turing and Ampere generations. Aside from learning significantly more comprehensive and accurate GPU TLB properties, we discover a design flaw of NVIDIA Multi-Instance GPU (MIG) feature. MIG claims full partitioning of the entire GPU memory system for secure GPU sharing in cloud computing. However, we surprisingly find that MIG does not partition the last-level TLB, which is shared by all the compute units in a GPU. Exploiting this design flaw and learned TLB properties, we are able to construct a covert channel for data exfiltration across MIG-enforced isolation. To the best of our knowledge, this is the first attack on MIG. We evaluate the proposed attack on a commercial cloud platform, and we successfully achieve reliable data exfiltration from a victim tenant at a speed of up to 31 kbps with a very high accuracy around 99.8%. Even when the victim is using the GPU for deep neural network training, the transmission can still reach more than 25 kbps with a more than 99.5% accuracy. We propose and implement a mitigation approach that can effectively thwart data exfiltration through this covert channel. Additionally, we present a preliminary study on exploiting the access patterns of the last-level TLB to infer the identity of applications running in other MIG-created GPU instances.
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 960-974
Open AccessT unne L s for B ootlegging: Fully Reverse-Engineering GPU TLBs for Challenging Isolation Guarantees of NVIDIA MIG
Recent studies have revealed much detailed information about the translation lookaside buffers (TLBs) of modern CPUs, but we find that many properties of such components in modern GPUs still remain unknown or unclear. To fill this knowledge gap, we develop a new GPU TLB reverse-engineering method and apply it to a variety of consumer- and server-grade GPUs in Turing and Ampere generations. Aside from learning significantly more comprehensive and accurate GPU TLB properties, we discover a design flaw of NVIDIA Multi-Instance GPU (MIG) feature. MIG claims full partitioning of the entire GPU memory system for secure GPU sharing in cloud computing. However, we surprisingly find that MIG does not partition the last-level TLB, which is shared by all the compute units in a GPU. Exploiting this design flaw and learned TLB properties, we are able to construct a covert channel for data exfiltration across MIG-enforced isolation. To the best of our knowledge, this is the first attack on MIG. We evaluate the proposed attack on a commercial cloud platform, and we successfully achieve reliable data exfiltration from a victim tenant at a speed of up to 31 kbps with a very high accuracy around 99.8%. Even when the victim is using the GPU for deep neural network training, the transmission can still reach more than 25 kbps with a more than 99.5% accuracy. We propose and implement a mitigation approach that can effectively thwart data exfiltration through this covert channel. Additionally, we present a preliminary study on exploiting the access patterns of the last-level TLB to infer the identity of applications running in other MIG-created GPU instances.
- 31 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 42 (11) , 3854-3867
STREAM: Toward READ-Based In-Memory Computing for Streaming-Based Processing for Data-Intensive Applications
With the rise of data intensive applications, traditional computing paradigms have hit the memory-wall. In-memory computing using emerging non-volatile memory (NVM) technology is a promising solution strategy to overcome the limitations of the von-Neumann architecture. In-memory computing using NVM devices has been explored in both analog and digital domains. Analog in-memory computing can perform matrix-vector multiplication (MVM) in an extremely energy-efficient manner. However, analog in-memory computing is prone to errors and resulting precision is therefore low. On the contrary, digital in-memory computing is a viable option for accelerating scientific computations that require deterministic precision. In recent years, several digital in-memory computing styles have been proposed. Unfortunately, state-of-the-art digital in-memory computing styles rely on repeated WRITE operations which involves switching of NVM devices. WRITE operations in NVM cells are expensive in terms of energy, latency and device endurance. In this paper, we propose a READ-based in-memory computing framework called STREAM. The framework performs streaming-based data processing for data-intensive applications. The STREAM framework consists of a synthesis tool that decomposes an arbitrary Boolean function into in-memory compute kernels. Two synthesis approaches are proposed to generate READ-based in-memory compute kernels using data structures from logic synthesis. A hardware/software co-design technique is developed to minimize the inter-crossbar data communication. The STREAM framework is evaluated using circuits from ISCAS85 benchmark suite, and Suite-Sparse applications to scientific computing. Compared with state-of-the-art in-memory computing framework, the proposed framework improves latency and energy performance with up to 200X and 20X, respectively.
- 31 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 42 (11) , 3854-3867
STREAM: Toward READ-Based In-Memory Computing for Streaming-Based Processing for Data-Intensive Applications
With the rise of data intensive applications, traditional computing paradigms have hit the memory-wall. In-memory computing using emerging non-volatile memory (NVM) technology is a promising solution strategy to overcome the limitations of the von-Neumann architecture. In-memory computing using NVM devices has been explored in both analog and digital domains. Analog in-memory computing can perform matrix-vector multiplication (MVM) in an extremely energy-efficient manner. However, analog in-memory computing is prone to errors and resulting precision is therefore low. On the contrary, digital in-memory computing is a viable option for accelerating scientific computations that require deterministic precision. In recent years, several digital in-memory computing styles have been proposed. Unfortunately, state-of-the-art digital in-memory computing styles rely on repeated WRITE operations which involves switching of NVM devices. WRITE operations in NVM cells are expensive in terms of energy, latency and device endurance. In this paper, we propose a READ-based in-memory computing framework called STREAM. The framework performs streaming-based data processing for data-intensive applications. The STREAM framework consists of a synthesis tool that decomposes an arbitrary Boolean function into in-memory compute kernels. Two synthesis approaches are proposed to generate READ-based in-memory compute kernels using data structures from logic synthesis. A hardware/software co-design technique is developed to minimize the inter-crossbar data communication. The STREAM framework is evaluated using circuits from ISCAS85 benchmark suite, and Suite-Sparse applications to scientific computing. Compared with state-of-the-art in-memory computing framework, the proposed framework improves latency and energy performance with up to 200X and 20X, respectively.
- 23 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 43 (5) , 8-15
Understanding and Characterizing Side Channels Exploiting Phase-Change Memories
Recent advances in non-volatile memory (NVM), together with their performance-optimized architectural schemes, position NVMs as promising building blocks for future main memory. However, the security of such techniques has not been explored. This article performs the first study on information leakage threats in phase change memories (PCM). We propose an attack framework, R-SAW, that systematically investigates side channel vulnerabilities in representative read techniques under inter-line and intra-line interleaving for multi-level cells. Our evaluation shows that the new side channels can accurately leak program secrets (e.g., crypto keys) and are extremely robust to noise. Our work highlights the need to understand microarchitecture security for emerging memory devices.
- 23 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 43 (5) , 8-15
Understanding and Characterizing Side Channels Exploiting Phase-Change Memories
Recent advances in non-volatile memory (NVM), together with their performance-optimized architectural schemes, position NVMs as promising building blocks for future main memory. However, the security of such techniques has not been explored. This article performs the first study on information leakage threats in phase change memories (PCM). We propose an attack framework, R-SAW, that systematically investigates side channel vulnerabilities in representative read techniques under inter-line and intra-line interleaving for multi-level cells. Our evaluation shows that the new side channels can accurately leak program secrets (e.g., crypto keys) and are extremely robust to noise. Our work highlights the need to understand microarchitecture security for emerging memory devices.