update ACE compiler framework paper info

_pubs/2024-10-10-cgo2025.md

@@ -1,10 +1,22 @@
 ---
 layout: pubs
 title:  "ANT-ACE paper was accepted by CGO 2025"
-brief:  "ACE framework - CGO 2025"
+brief:  "ACE compiler framework - CGO 2025"
 date:   2024-10-10 09:41:09
 author: cmplr
 ---
 
-"ACE: An FHE Compiler Framework for Automating Neural Network Inference" was accepted by CGO 2025.
+## ANT-ACE: An FHE Compiler Framework for Automating Neural Network Inference
+
+### Abstract
+
+Fully Homomorphic Encryption (FHE) facilitates compu- tations on encrypted data without requiring access to the decryption key, offering substantial privacy benefits for de- ploying neural network applications in sensitive sectors such as healthcare and finance. Nonetheless, programming these applications within the FHE framework is complex and de- mands extensive cryptographic expertise to guarantee cor- rectness, performance, and security.
+
+In this paper, we present ANT-ACE, a production-quality, open-source FHE compiler designed to automate neural net- work inference on encrypted data. ANT-ACE accepts ONNX models and generates C/C++ programs, leveraging its cus- tom open-source FHE library. We explore the design chal- lenges encountered in the development of ANT-ACE, which is engineered to support a variety of input formats and ar- chitectures across diverse FHE schemes through a novel Intermediate Representation (IR) that facilitates multiple lev- els of abstraction. Comprising 44,000 lines of C/C++ code, ANT-ACE efficiently translates ONNX models into C/C++ programs for encrypted inference on CPUs, specifically uti- lizing the RNS-CKKS scheme. Preliminary evaluations on a single CPU indicate that ANT-ACE achieves significant speed enhancements in ResNet models, surpassing expert manual implementations and fulfilling our design goals.
+
+### ACM Reference Format
+
+Long Li, Jianxin Lai, Peng Yuan, Tianxiang Sui, Yan Liu, Qing Zhu, Xiaojing Zhang, Linjie Xiao, Wenguang Chen, and Jingling Xue. 2025. ANT-ACE: An FHE Compiler Framework for Automating Neural Network Inference. In Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization (CGO ’25), March 01–05, 2025, Las Vegas, NV, USA. ACM, New York, NY, USA, 16 pages. https://doi.org/10.1145/3696443.3708924
+
+[[Paper Download]] (assets/ACE_paper.pdf)