A September 2023 presentation by a MESA-affiliated researcher (name redacted), delivered at a company called "中电积至（海南）信息技术有限公司" and footer-branded with the internal lab name "网络空间主权保障技术研究实验室" ("Cyberspace Sovereignty-Guarantee Technology Research Laboratory"), lays out three institutional strategies for governing encrypted traffic: (1) decrypt via client-side scanning/key-logging (citing Facebook's on-device pre-encryption content-moderation scanning and SSLKEYLOGFILE harvesting) or CDN "keyless" proxies and middlebox certificates, (2) classify traffic without decrypting it, and (3) reputation-score both communicating parties using network-mapping (测绘) results.

The same 2024 IIE CAS thesis proposes 'PED' (Packet-context based Evasion Detection): an XGBoost flow-feature pre-filter followed by a GRU-based autoencoder trained on packet-context features (inter-packet plus protocol-layer, including HTTP-layer fields) that flags DPI-evasion traffic via reconstruction error, reporting accuracy/ROC-AUC above 0.88/0.97 and generalizing to the public CICIDS and MAWI datasets; the thesis also proposes a deployable LAN-gateway evasion-detection prototype and four DPI-middlebox hardening recommendations (mimic Suricata's strict field validation, enforce RFC-compliant parsing, add ML-based anomaly detection, run regular red-team evaluations).

An IIE CAS technical whitepaper for the "High-speed Network Traffic Processing and Analysis System" names the "MESA" team (处理架构组MESA团队, "Massive Effective Stream Analysis") as part of IIE's Second Research Office, lists deployment case studies at China's National Administration of State Secrets Protection (国家保密局), the National Computer Network and Information Security Management Center, Guangdong provincial e-government services, and CNCERT (国家互联网应急中心), and gives a named IIE contact (name/phone/email redacted here). The product classifies behavior inside encrypted tunnels (remote control, audio/video calls, encrypted mail, VPN) and dozens of IM/social apps via SSL/SSH/IPSEC/QUIC/SOCKS protocol detection.

An internal schema doc describes an 'Unknown Protocol Identification Database': an Elasticsearch port-asset table tracking active/passive/fused protocol-type guesses and banner text per IP:port, feeding a MySQL clustering pipeline (cluster_info/cluster_task) that groups unclassified traffic by a 'fingerprint' field into named-protocol clusters -- an unsupervised discovery pipeline for identifying and naming new/unknown protocols at scale, distinct from MAAT/AppSketch's signature-matching against already-known protocols.

A CAS-institute thesis on differentiating human vs. automated ("machine") network behavior deploys an HTTP/SSL key-field extraction and app-identification system at a live network gateway (mirrored traffic) built on a modified nDPI (extended to recognize 108 application-layer protocols) plus a custom rule-scan module whose region/group/compile config hierarchy and terminology closely parallel MAAT's separately-documented architecture, suggesting shared lineage between this academic prototype and MAAT's production rule engine.

A 2024 University of Chinese Academy of Sciences course taught within MESA Lab's research group (instructor name redacted) trains students to fingerprint and detect censorship-measurement tools -- OONI Probe's fixed built-in control-server domains, ICLab's User-Agent behavior, and the large-domain-fan-out pattern shared by Satellite/Iris/Quack/GFWatch -- and to build ML classifiers (citing IEEE Access 2019, CoNeXT 2019 CLAP, and USENIX 2023 ML-TRW) that detect DPI-evasion probing traffic in the style of Geneva and StateDiver, explicitly framed as protecting DPI middleware from being probed and evaded.

Reveals internal architecture of TSG's traffic classification engine: the 'sapp' process (binary at /opt/tsg/sapp/sapp, version sapp-4.2.90) uses a packet-I/O layer called 'marsio', a custom app-identification plugin 'app_sketch_local' (identify_app_by_tcp_payload / identify_app_by_user_define_attributes), and an embedded LuaJIT ('libelua') for user-defined protocol signatures (e.g. custom Modbus detection) — concurrent LUA script loading crashes the classification worker.