Evidence search
Search
Search titles, summaries, topics, providers, authors, and the full open-access corpus.
Results for “Ai Systems”
38 publicationsSecurity evidence for AI release decisions
A release approval should identify the changed application, the claims its tests support and the evidence that expires when a model, prompt, data path or runtime changes.
AI systems · By Cloud Security DeskWhat coding benchmarks can prove about a model
A coding benchmark result depends on its tasks, harness and tests. A reproducible count of SWE-bench Verified shows why the denominator belongs beside every comparison.
AI systems · By Cloud Security DeskWhere fine tuning data needs a trust boundary
A training dataset can preserve its checksum and still teach the wrong behavior. Admission controls need to separate origin, transformation, approved use and the model change they produce.
AI systems · By Cloud Security DeskA budget model for bounded AI inference
Request throttles, token quotas and billing alerts control different things. An inference service needs an admission decision that reserves bounded work and reconciles what actually ran.
AI systems · AWS / Kubernetes / vLLM · By Cloud Security DeskAn evidence plan for AI incident response
An AI incident record needs to connect the system version, context, output, downstream action and observed consequence. A saved prompt or a public report is only part of that evidence.
AI systems · By Cloud Security DeskModel output needs its own trust boundary
A model can produce valid JSON containing an unauthorized identifier, an unsafe link or text that a renderer interprets as code. The application consuming that output owns the next trust decision.
AI systems · OpenAI · By Cloud Security DeskMap every connection beyond the private AI endpoint
Trace inference, retrieval, tools, administration, and telemetry separately before describing an AI application as private.
AI systems · AWS · By Cloud Security DeskKeep sensitive prompts out of routine telemetry
Collect diagnostic metadata for a defined purpose and treat prompts, retrieved documents, tool arguments, and responses as a separate content-capture decision.
AI systems · AWS · By Cloud Security DeskPut enforceable boundaries around agent tool calls
Treat model proposals as requests for authority, then check the operation, resource, recipient, and approval at the point where a tool can create a side effect.
AI systems · AWS · By Cloud Security DeskTreat model downloads as software supply chain changes
Review weights, custom code, dependencies, and runtime authority as separate decisions before promoting a downloaded model into a trusted environment.
AI systems · Hugging Face · By Cloud Security DeskKeep MCP tokens bound to the intended resource
Keep token audiences, user consent, and downstream tool authority separate when reviewing a protected HTTP MCP service.
AI systems · MCP · By Cloud Security DeskKeep private documents out of shared RAG answers
Authorize retrieved documents before they enter model context, preserve permissions on chunks, and make source access changes visible in the retrieval path.
AI systems · Azure · By Cloud Security DeskQwen3.8-Flash-Next and GLM-5.3-Flash share a 3:1 long-context pattern
Both models replace most conventional attention layers with recurrent state and reserve sparse attention for periodic retrieval. Their differences lie in where they place capacity, how much neural computation they activate, and what their serving stacks must keep trustworthy.
AI systems · Resilience · By Umair Akbar and Ahmed ElshekhThreat-model the system around the model
The model endpoint is one component. The consequential paths often run through retrieval stores, orchestration identities, evaluation data, and operator tools.
AI systems · AWS / Azure / Google Cloud · By Umair Akbar and Ahmed Elshekh