All news with #rag security tag

🔒 Microsoft describes attacks targeting AI infrastructure components such as gateways, retrieval platforms, orchestration services, and container runtimes that centralize credentials and execution privileges. Observed intrusions against LiteLLM, RAGFlow, and Kestra aimed to harvest secrets, persist on hosts, and monetize compute. The advisory emphasizes inventorying exposed AI surfaces, restricting administrative access, and monitoring gateway-originated execution and secret access to mitigate risk.

🗂️ Box and Google Cloud are integrating Gemini Multimodal Embeddings 2 into Box's Agentic Platform to extend RAG beyond text and enable unified search and reasoning across documents, images, tables, and charts. This integration preserves spatial and visual structure, supports crossmodal retrieval, and bridges heterogeneous formats like .docx, .xlsx, .pdf, and .pptx. The combined system targets use cases in finance, healthcare, and enterprise auditing by enabling layout-aware embeddings, cross-file synthesis, and visual-to-text auditing.

🔔 Amazon announced general availability of Amazon Nova Multimodal Embeddings in AWS GovCloud (US-West). The unified embedding model supports text, documents, images, video, and audio through a single model to enable cross-modal retrieval and agentic RAG. It accepts up to 8K tokens and video/audio segments up to 30 seconds, with synchronous and asynchronous API options for latency-sensitive and bulk workloads.

🟦 Amazon S3 Vectors is now available in the AWS European Sovereign Cloud (Germany) Region. Amazon S3 Vectors is purpose-built vector storage for AI agents, inference, Retrieval Augmented Generation (RAG), and semantic search at billion-vector scale. It offers the elasticity, durability, and availability of Amazon S3 with dedicated APIs to store, access, and query vectors without provisioning infrastructure.

🔍 BigQuery announced GA for Autonomous Embedding Generation and AI.SEARCH(), plus a public preview of Hybrid Search to simplify retrieval and analytics over unstructured data. It automates embedding creation (including images), offers large single-query performance gains, and combines semantic and lexical techniques for more precise results. These features integrate into a broader end-to-end document analytics workflow in BigQuery.

🧭 AlloyDB introduces native AI Functions to solve tokenization issues for logographical languages like Chinese, Japanese, and Korean. By calling Gemini models from SQL via ai.generate(), developers can perform in-database segmentation, stop-word removal, and embedding generation without ETL pipelines or external services. The approach uses stored-procedure batching, generated columns for search vectors and embeddings, and RUM plus ScaNN indexes to enable fast hybrid lexical and semantic search.

🔔 Amazon S3 Vectors is now available in AWS GovCloud (US-East) and AWS GovCloud (US-West). The service offers purpose-built vector storage for AI agents, inference, Retrieval Augmented Generation (RAG), and semantic search at billion-vector scale. S3 Vectors provides the elasticity, durability, and availability of Amazon S3 with dedicated APIs to store, access, and query vectors without provisioning infrastructure. Check AWS Regions and endpoints for the full availability list.

🚀 Amazon RDS for Oracle now supports Oracle Database 26ai, Oracle's Long Term Support release, with integration to Amazon Bedrock providing access to foundation models such as Anthropic Claude, Amazon Nova, and Meta Llama. Oracle Database 26ai enables Select AI for generating and running SQL from natural language prompts and supports in-database RAG via Oracle AI Vector Search, avoiding the need for a separate vector store. The release also offers JSON Relational Duality Views and SQL Property Graphs and is available in Enterprise Edition across commercial and GovCloud regions.

📡 Modern telecom networks require domain-specific AI because general models lack the precise, vendor-specific context needed for mission-critical operations. GSMA’s Open Telco AI platform and AT&T’s OTel family—fine-tuned on Google’s open-source Gemma models—use curated telco datasets and RAG-based abstention to reduce hallucinations. The initiative produced 30 optimized models, demonstrated strong Gemma performance in AT&T tests, and already exceeded 18 million downloads.

🚀 Amazon Bedrock Managed Knowledge Base is now generally available as a fully managed retrieval-augmented generation (RAG) service. The offering removes the need to manage vector databases, data pipelines, and retrieval infrastructure by handling ingestion, storage optimization, and advanced retrieval. It supports six native connectors—S3, SharePoint, Confluence, Google Drive, OneDrive, and a web crawler—with automatic syncing and managed vector storage tuned for price-performance. Native integration with Amazon Bedrock AgentCore provides auto-generated permissions and observability for agent deployments.

🔍 Amazon S3 Vectors now returns up to 10,000 similarity search results per query, a 100x increase from the prior limit. This larger topK helps applications retrieve a more comprehensive candidate set for multi-stage pipelines that perform reranking, aggregations, or deduplication. Use the latest AWS SDK and specify up to 10,000 results in QueryVectors; results are paginated so you can process the first page while additional pages are fetched. A small data-returned fee applies beyond the free 512 KB per query.

🔎 Foundry IQ streamlines bringing enterprise and external knowledge into agent workflows by unifying content, improving ingestion, and offering a serverless model for retrieval. The service provides a Model Context Protocol (MCP) server, integrates Microsoft Web IQ for low-latency external context, and includes GA security and compliance features. Serverless Developer tier is in public preview with CU-based billing estimates and scale-to-zero capacity.

⚠️ A max-severity flaw (CVE-2026-45829) in the Python FastAPI server of ChromaDB allows unauthenticated attackers to load and execute remote models before authentication is enforced, enabling arbitrary code execution on exposed servers. The issue impacts PyPI-distributed releases used widely in AI retrieval stacks; a 1.5.9 release exists but it is unclear if the fix addresses this vulnerability. Mitigations include using the Rust frontend, avoiding public exposure of the Python API, and restricting network access to the ChromaDB API port.

🔒 A hands-on April 2026 experiment shows how quickly attackers can target private AI servers: a Raspberry Pi honeypot posed as a high-performance stack (Ollama, LM Studio, AutoGPT, LangServe, text-gen-webui) and claimed a local Qwen3-Coder 30B instance plus RAG/MCP assets. Shodan discovered the server within three hours and, over a month, it logged 113,000+ requests from thousands of IPs with 23% probing AI capabilities. Observed tactics included fingerprinting endpoints like /v1/models and /.well-known/mcp.json and systematic hunts for exposed .env files, highlighting the importance of securing RAG, MCP and private AI deployments from day one.

🔒 Enterprise SaaS products increasingly adopt Retrieval-Augmented Generation (RAG) to give AI agents access to customer-specific knowledge, but that bridge also creates severe security liabilities. The article reviews recent high-profile failures — from the EchoLeak zero-click exfiltration to vector database reconstructions, indirect prompt injections in IDEs and large-scale knowledge-base poisoning — and breaks down the typical three-phase RAG architecture: ingestion & embedding, vector storage & retrieval, and LLM generation. It advocates a defense-in-depth posture combining pre-ingest DLP, retrieval-time RBAC/ABAC, prompt isolation and output filtering, and highlights Google Cloud services like Cloud DLP, Vertex AI vector search, Vertex AI model armor and Security Command Center to operationalize those controls.

🔍 Cloudflare introduced AI Search, a plug-and-play search primitive that provides a unified retrieval layer for agents, support bots, and coding assistants. It pairs hybrid semantic (vector) and BM25 keyword matching, managed storage, and built-in vector indexes so developers can create instances at runtime without provisioning separate infrastructure. The service integrates with Workers, the Agents SDK, and Wrangler, supports metadata boosts and cross-instance queries, and can optionally rerank results with a cross-encoder.

🔍 QueryData launches in preview, offering near-100% accuracy translating natural language into database queries across AlloyDB, Cloud SQL (MySQL and PostgreSQL) and Spanner. Built on Google Cloud’s Gemini LLM and augmented by rich database context, it uses schema ontologies, query blueprints and ambiguity detection to generate precise queries. Deterministic security is enforced via Parameterized Secure Views (PSVs), and integration is supported through a unified QueryData API, the MCP Toolbox for Databases, and context-engineering tools including an Evalbench framework.

🚀 Amazon expanded S3 Vectors into 17 additional AWS Regions — now available in 31 Regions worldwide. S3 Vectors is the first cloud object storage with native vector support, built for AI agents, inference, Retrieval-Augmented Generation (RAG), and semantic search at billion-vector scale. It supports up to two billion vectors per index, elastic scaling to 10,000 vector indexes per bucket, low-latency queries (frequent queries as fast as 100 ms; infrequent under one second), and native integration with Amazon Bedrock Knowledge Bases to help reduce RAG costs.

🔍Spanner positions itself as a unified, globally consistent database designed for agentic AI by combining relational, key-value, graph, vector and full-text search capabilities in one platform. The post argues this interoperable multi-model approach reduces data silos, removes brittle synchronization logic, and improves governance, availability, and development velocity. Google highlights features such as GQL graph support, a Cassandra native endpoint for lift-and-shift, and ScaNN-based ANN vector search. The customer example of MakeMyTrip illustrates significant operational simplification and faster AI feature delivery.

🤖RSA Conference 2026 reframes AI from a single track to the event itself, with roughly 40% of sessions AI-weighted and artificial intelligence woven across identity, cloud, threat intelligence and human-focused tracks. CISOs face a dual mandate: accelerate AI adoption to remain competitive while protecting the enterprise from new attack surfaces such as RAG pipelines, vector databases, prompt injection and model inversion. Key priorities at RSAC include securing the AI stack, defining AI governance and compliance (including preparation for the EU AI Act), managing non‑human identities, mitigating shadow AI and AI-assisted coding risks, and preparing SOCs for autonomous remediation.