Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910151783481344 |
|---|---|
| author | Fu, Rong Ma, Xiaowen Liu, Kun Wu, Wangyu Kong, Ziyu Tan, Jia Yee Luo, Tailong Li, Xianda Su, Zeli Wang, Youjin Liu, Yongtai Fong, Simon |
| author_facet | Fu, Rong Ma, Xiaowen Liu, Kun Wu, Wangyu Kong, Ziyu Tan, Jia Yee Luo, Tailong Li, Xianda Su, Zeli Wang, Youjin Liu, Yongtai Fong, Simon |
| contents | Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and the need for predictable, auditable behavior. Chimera introduces a principled framework that maps attention-oriented neural computations and symbolic constraints onto dataplane primitives, enabling trustworthy inference within the match-action pipeline. Chimera combines a kernelized, linearized attention approximation with a two-layer key-selection hierarchy and a cascade fusion mechanism that enforces hard symbolic guarantees while preserving neural expressivity. The design includes a hardware-aware mapping protocol and a two-timescale update scheme that together permit stable, line-rate operation under realistic dataplane budgets. The paper presents the Chimera architecture, a hardware mapping strategy, and empirical evidence showing that neuro-symbolic attention primitives can achieve high-fidelity inference within the resource envelope of commodity programmable switches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12851 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence Fu, Rong Ma, Xiaowen Liu, Kun Wu, Wangyu Kong, Ziyu Tan, Jia Yee Luo, Tailong Li, Xianda Su, Zeli Wang, Youjin Liu, Yongtai Fong, Simon Networking and Internet Architecture Artificial Intelligence Cryptography and Security Machine Learning Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and the need for predictable, auditable behavior. Chimera introduces a principled framework that maps attention-oriented neural computations and symbolic constraints onto dataplane primitives, enabling trustworthy inference within the match-action pipeline. Chimera combines a kernelized, linearized attention approximation with a two-layer key-selection hierarchy and a cascade fusion mechanism that enforces hard symbolic guarantees while preserving neural expressivity. The design includes a hardware-aware mapping protocol and a two-timescale update scheme that together permit stable, line-rate operation under realistic dataplane budgets. The paper presents the Chimera architecture, a hardware mapping strategy, and empirical evidence showing that neuro-symbolic attention primitives can achieve high-fidelity inference within the resource envelope of commodity programmable switches. |
| title | Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence |
| topic | Networking and Internet Architecture Artificial Intelligence Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2602.12851 |