ValQID: Learning the Net Value of Semantic Query Groups for Web Device Identification
Organizations: National University of Defense Technology, Changsha, China · Xiamen University, Xiamen, China
Abstract
Web interfaces are widely used to access network services and manage networked devices. Identifying the vendors and types of devices behind Web interfaces is a critical step in asset inventory, security management, and risk assessment. Device identity cues are dispersed across page text, configuration fields, and management functions, and interpreting them often requires linking related Web objects. Responses and objects require different amounts of semantic analysis, so exhaustively processing all candidate content can introduce unnecessary computation. We present ValQID, which uses a relation graph to combine dispersed device identity cues, evaluates semantic questions efficiently with DSEJEV, and accounts for complementarity among semantic questions when estimating computation value. Based on the current identification state, ValQID weighs each question group's expected identification benefit against its execution cost and adaptively allocates computation to identify device vendors and types. Evaluation on real Web response data shows that ValQID achieves relative gains of up to 47.1% in joint macro-F1 and up to 82.1% in macro-F1 for low-frequency vendors over a state-of-the-art method. DSEJEV speeds up semantic processing by up to 8.58 times compared with general-purpose language models.
Figures & tables
| Method | Identification technique | Identification modeling | Computation control | |||
|---|---|---|---|---|---|---|
| Language models | Adaptation | Relations | Adaptive | Cost-aware | ||
| ARE ( Feng et al., 2018 ) | Association rule mining | |||||
| WYSIWYG ( Wang et al., 2022b ) | CNN classification; OCR text matching | |||||
| DevTag ( Wan et al., 2023 ) | Entity and relation extraction | |||||
| LDF ( Sarabi et al., 2023 ) | Contrastive RoBERTa; clustering | |||||
| BLMProbe ( Tian et al., 2025 ) | LLM labeling; BERT classification | |||||
| Dataset | Method | Vendor Identification | Device-Type Identification | Joint Identification | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Acc. | Prec. | Rec. | M-F1 | Acc. | Prec. | Rec. | M-F1 | Acc. | M-F1 | ||
| DevTag | DevTag ( Wan et al., 2023 ) | 57.18 40.4% | 51.19 37.4% | 47.09 35.8% | 45.35 39.9% | 58.50 39.2% | 39.36 58.8% | 28.61 68.7% | 31.18 66.3% | 55.58 41.7% | 38.49 49.1% |
| RoBERTa ( Sarabi et al., 2023 ) | 89.36 6.8% | 38.82 52.5% | 33.19 54.8% | 33.82 55.2% | 89.45 7.1% | 46.74 51.0% | 44.56 51.2% | 45.18 51.2% | 86.10 9.7% | 27.05 64.2% | |
| BLMProbe ( Tian et al., 2025 ) | 92.71 3.3% | 58.85 28.0% | 59.08 19.5% | 55.97 25.9% | 93.66 2.7% | 73.81 22.7% | 84.03 8.0% | 77.07 16.8% | 91.99 3.5% | 56.25 25.7% | |
| Qwen3.5 ( Qwen Team, 2026 ) | 70.27 26.7% | 31.42 61.6% | 28.39 61.3% | 26.38 65.1% | 35.50 63.1% | 22.75 76.2% | 10.11 88.9% | 10.91 88.2% | 32.46 65.9% | 13.26 82.5% | |
| ValQID (Ours) | 95.91 | 81.76 | 73.38 | 75.50 | 96.30 | 95.46 | 91.33 | 92.62 | 95.30 | 75.65 | |
| Dataset | Configuration | Vendor | Device type | Joint identification | Semantic queries | Input tokens | |
|---|---|---|---|---|---|---|---|
| M-F1 | M-F1 | Acc. | M-F1 | ( ) | ( ) | ||
| DevTag | ValQID | 75.50 | 92.63 | 95.31 | 75.66 | ||
| w/o Semantic Queries | 38.55 | 62.03 | 88.21 | 39.11 | — | — | |
| w/o Character Branch and Fusion | 38.65 | 60.73 | 89.32 | 35.40 | |||
| w/o Value-based Query Selection | 75.56 | 92.63 | 95.32 | 75.70 | |||
| BLMProbe | ValQID | 93.28 | 98.34 | 96.63 | 91.90 | ||
| No. | Target object and context | Semantic question | Candidate answers |
|---|---|---|---|
| 1 | A form with credential inputs and login controls | What is the semantic function of the detected form element? | insufficient_evidence ; collects_user_credentials ; submits_configuration_data ; displays_error_messages ; handles_media_upload |
| 2 | A submission operation linked to the form | What is the primary operational purpose of the detected event handler? | insufficient_evidence ; initiates_page_load ; handles_user_interaction ; manages_window_dimensions ; triggers_form_submission |
| Pair 1–2: Operation form. | |||
| 3 | An external script element and page language cues | What is the observable function role of the script identified by the src attribute? | insufficient_evidence ; dependency_loading ; localization_execution ; framework_initialization |
| 4 | An external resource referenced by a script, with its reference context | What is the observable function role of the resource identified by the path attribute? | insufficient_evidence ; styling_definition ; favicon_representation ; application_bundle ; localization_script |
| Pair 3–4: Script resource. | |||