Websites & public assets
Monitor content, visual and browser-behavior anomalies across public-sector, education and enterprise websites.
Xingju Tianshu
Website Security, Content Compliance & AI Input Monitoring
Visible website risks. Actionable monitoring signals.
Visible website risks. Actionable monitoring signals.
Xingju Tianshu Security Operations Center monitors websites and public digital assets for content compliance and intrusion signals. It cross-checks page content, visual changes, browser behavior, access identities and regional egress, connecting detection with human confirmation and rule operations.
Use cases
For website monitoring, content compliance and web inputs to AI
Content-compliance operations
Connect suspicious-content detection, human review, false-positive feedback, variant grouping and rule approval to develop lexicons.
Web inputs to AI
Check indirect prompt-injection signals that people may miss in pages consumed by AI assistants and RAG workflows.
Distribution cross-checks
Compare access identities, rendering modes and regional egress to verify visitor-targeted anomalies.
From multiple signals to operational feedback
Cross-check signals across engines. AI assists assessment but does not determine final alerts. Content compliance depends on lexicon coverage, updates and ongoing operation.
- Collect perspectives
Collect according to access identity, rendering mode and node scope.
- Cross-check engines
Correlate content, visual, behavioral and AI-input signals.
- Confirm & handle
Review suspicious signals in context and follow up.
- Feed back & operate
Review false positives and new variants, updating approved rules and lexicons.
Cross-check signals across engines. AI assists assessment but does not determine final alerts. Content compliance depends on lexicon coverage, updates and ongoing operation.
Product capabilities
Defacement signatures
Identify defacement signatures without historical baselines, including sites with existing anomalies.
Sensitive-content detection
Provide five-category scoring, variant decoding, allowlists and feedback; outcomes depend on lexicon coverage, updates and customer-specific operation.
Visual-change detection
Combine full-page capture, perceptual hashes and pixel differences to identify visual anomalies despite similar text.
Multi-view rendering
Compare distribution across ten perspectives, including desktop, mobile, search crawlers, AI crawlers and no-JavaScript rendering.
Runtime behavior analysis
Observe dynamic injection, encoded execution, delayed callbacks, redirects and internal-network probing signals in a browser sandbox.
AI input-surface security
Check hidden elements, HTML comments, attributes, zero-width text and encoded payloads for prompt injection. AI assistance does not decide final alerts.
Distributed perspectives
Cross-check multiple cloud nodes for anomalous content targeted by region or egress IP.
Evaluation results & scope
The company release reports results for its stated version and internal samples: 95.7% detection across 70 archived defaced pages; 0.0% sample false positives across 11 normal sites and 41 normal pages; and 51 passes, four partially available results and zero failures across 55 end-to-end checks.
These are the release article’s internal evaluation results, not universal accuracy or SLA commitments. Reported remaining misses mainly involve replaced GIF and JPG image files; additional image-content comparison is planned.
The content-compliance engine framework is available, while its lexicons still require continued development and operation. Use results with customer-specific context, human confirmation and feedback.
Deployment & services
Supports private deployment with encrypted cloud and model credentials. Domestic or local model interfaces can retain data within the customer network. External YAML rules support hot reload, with YARA integration; confirm model interfaces and node scope for the deployment environment.
Talk to us about business fit, product demonstrations and implementation.