All news with #retrieval-augmented generation tag

AI in Today's Cybersecurity: Detection, Hunting, Response

🤖 Artificial intelligence is reshaping how organizations detect, investigate, and respond to cyber threats. The article explains how AI reduces alert noise, prioritizes vulnerabilities, and supports behavioral analysis, UEBA, and NLP-driven phishing detection. It highlights Wazuh's integrations with models such as Claude 3.5, Llama 3, and ChatGPT to provide conversational insights, automated hunting, and contextual remediation guidance.

AWS Knowledge MCP Server Now Generally Available Globally

🔎 The AWS Knowledge MCP Server is now generally available, giving AI agents and MCP-compatible clients access to authoritative AWS documentation, blog posts, What's New announcements, and Well-Architected guidance in an LLM-friendly format. The GA release also adds structured knowledge about regional API and CloudFormation resource availability. The server is publicly accessible at no cost and does not require an AWS account, though usage is rate-limited. Configure MCP clients to use the AWS Knowledge MCP Server endpoint to anchor agent responses in trusted AWS context and reduce manual context management.

Adapting Enterprise Risk Management for Generative AI

🛡️ This post explains how to adapt enterprise risk management frameworks to safely scale cloud-based generative AI, combining governance foundations with practical controls. It emphasizes the cloud as the foundational infrastructure and identifies differences from on‑premises models that change risk profiles and vendor relationships. The guidance maps traditional ERMF elements to AI-specific controls across fairness, explainability, privacy/security, safety, controllability, veracity/robustness, governance, and transparency, and references tools such as Amazon Bedrock Guardrails, SageMaker Clarify, and the ISO/IEC 42001 standard to operationalize those controls.

Enabling AI Sovereignty Through Choice and Openness Globally

🌐 Cloudflare argues that AI sovereignty should mean choice: the ability for nations to control data, select models, and deploy applications without vendor lock-in. Through its distributed edge network and serverless Workers AI, Cloudflare promotes accessible, low-cost deployment and inference close to users. The company hosts regional open-source models—India’s IndicTrans2, Japan’s PLaMo-Embedding-1B, and Singapore’s SEA-LION v4-27B—and offers an AI Gateway to connect diverse models. Open standards, interoperability, and pay-as-you-go economics are presented as central to resilient national AI strategies.

Cloudflare Launches Content Signals Policy for robots.txt

🛡️ Cloudflare introduced the Content Signals Policy, an extension to robots.txt that lets site operators express how crawlers may use content after it has been accessed. The policy defines three machine-readable signals — search, ai-input, and ai-train — each set to yes/no or left unset. Cloudflare will add a default signal set (search=yes, ai-train=no) to managed robots.txt for ~3.8M domains, serve commented guidance for free zones, and publish the spec under CC0. Cloudflare emphasizes signals are preferences, not technical enforcement, and recommends pairing them with WAF and Bot Management.

Responsible AI Bot Principles to Protect Web Content

🛡️ Cloudflare proposes five practical principles to guide responsible AI bot behavior and protect web publishers, users, and infrastructure. The framework stresses public disclosure, reliable self-identification (moving toward cryptographic verification such as Web Bot Auth), a declared single purpose for crawlers, and respect for operator preferences via robots.txt or headers. Operators must also avoid deceptive or high-volume crawling, and Cloudflare invites multi-stakeholder collaboration to refine and adopt these norms.

INDOT Used Google AI to Save 360 Hours and Meet Deadline

🚀 Indiana Department of Transportation built a week-long pilot on Google Cloud to meet a 30-day executive order, using a Retrieval-Augmented Generation workflow that combined rapid ETL, Vertex AI Search indexing, and Gemini. The system scraped and parsed decades of internal policies and manuals, produced draft reports across nine divisions with 98% fidelity, and saved an estimated 360 hours of manual effort, enabling INDOT to submit on time.

Deutsche Bank launches DB Lumina for AI research platform

🤖 DB Lumina is Deutsche Bank Research’s AI-powered assistant, built on Google Cloud and integrating multimodal Gemini models, RAG retrieval, and vector search. It provides a conversational chat interface, reusable prompt templates, and document-grounded answers with inline citations and enterprise guardrails for compliance. Early deployment to roughly 5,000 analysts has yielded measurable time savings, deeper analysis, and improved editorial accuracy.

Cloudflare 2025 Founders’ Letter: AI, Content, and Web

📣 Cloudflare’s 2025 Founders’ Letter reflects on 15 years of Internet change, highlighting encryption’s rise thanks in part to Universal SSL, slow IPv6 adoption, and the rising costs of scarce IPv4 space. It warns that AI answer engines are shifting value away from traffic-based business models and threatening publishers. Cloudflare previews tools and partnerships — including AI Crawl Control — to help creators control access and negotiate compensation.

Source-of-Truth Authorization for RAG Knowledge Bases

🔒 This post presents an architecture to enforce strong, source-of-truth authorization for Retrieval-Augmented Generation (RAG) knowledge bases using Amazon S3 Access Grants with Amazon Bedrock. It explains why vector DB metadata filtering is insufficient—permission changes can be delayed and complex identity memberships are hard to represent—and recommends validating permissions at the data source before returning chunks to an LLM. The blog includes a practical Python walkthrough for exchanging identity tokens, retrieving caller grant scopes, filtering returned chunks, and logging withheld items to reduce the risk of sensitive data leaking into LLM prompts.

Mr. Cooper and Google Cloud Build Multi-Agent AI Team

🤖 Mr. Cooper partnered with Google Cloud to develop CIERA, a modular agentic AI framework that assembles specialized agents to support mortgage servicing representatives and customers. The design assigns distinct roles — orchestration, task execution, data retrieval, memory, and evaluation — while keeping humans in the loop for verification and personalization. Built on Vertex AI, CIERA aims to reduce research time, lower average handling time, and preserve trust and compliance in regulated workflows.

Seattle Children’s Uses AI to Accelerate Pediatric Care

🤖 Seattle Children’s partnered with Google Cloud to build Pathway Assistant, a multimodal AI chatbot that turns thousands of pediatric clinical pathway PDFs into conversational, searchable guidance. Using Vertex AI and Gemini, the assistant extracts JSON metadata, parses diagrams and flowcharts, and returns cited answers in seconds. The tool logs clinician feedback to BigQuery and stores source documents in Cloud Storage, enabling continuous improvement of documentation and metadata.

New LLM Attack Vectors and Practical Security Steps

🔐This article reviews emerging attack vectors against large language model assistants demonstrated in 2025, highlighting research from Black Hat and other teams. Researchers showed how prompt injections or so‑called promptware — hidden instructions embedded in calendar invites, emails, images, or audio — can coerce assistants like Gemini, Copilot, and Claude into leaking data or performing unauthorized actions. Practical mitigations include early threat modeling, role‑based access for agents, mandatory human confirmation for high‑risk operations, vendor audits, and role‑specific employee training.

Check Point Acquires Lakera to Build AI Security Stack

🔐 Check Point has agreed to acquire Lakera, an AI-native security platform focused on protecting agentic AI and LLM-based deployments, in a deal expected to close in Q4 2025 for an undisclosed sum. Lakera’s Gandalf adversarial engine reportedly leverages over 80 million attack patterns and delivers detection rates above 98% with sub-50ms latency and low false positives. Check Point will embed Lakera into the Infinity architecture, initially integrating into CloudGuard WAF and GenAI Protect, offering near-immediate, API-based protection as an add-on for existing customers.

OWASP LLM AI Cybersecurity and Governance Checklist

🔒 OWASP has published an LLM AI Cybersecurity & Governance Checklist to help executives and security teams identify core risks from generative AI and large language models. The guidance categorises threats and recommends a six-step strategy covering adversarial risk, threat modeling, inventory and training. It also highlights TEVV, model and risk cards, RAG, supplier audits and AI red‑teaming to validate controls. Organisations should pair these measures with legal and regulatory reviews and clear governance.

Gemini and Open-Source Text Embeddings Now in BigQuery ML

🚀 Google expanded BigQuery ML to generate embeddings from Gemini and over 13,000 open-source text-embedding models via Hugging Face, all callable with simple SQL. The post summarizes model tiers to help teams trade off quality, cost, and scalability, and introduces Gemini's Tokens Per Minute (TPM) quota for throughput control. It shows a practical workflow to deploy OSS models to Vertex AI endpoints, run ML.GENERATE_EMBEDDING for batch jobs, and undeploy to minimize idle costs, plus a Colab tutorial and cost/scale guidance.

Avnet Reclaims Security Data, Cuts Costs, Boosts AI

🔐 Avnet moved away from vendor-bound SIEM, EDR and RBVM silos toward a centralized security data pipeline built on Cribl, prompted by a legacy SIEM renewal that became a strategy inflection point. The redesign gave Avnet full ownership of telemetry, enabled large-scale ETL and flexible routing, and freed analysts from vendor dashboards. Operationally, licensing and storage costs dropped dramatically to 15% of prior levels while processing capacity doubled and pipeline staffing fell from four engineers to one. With its own data layer in place, Avnet is accelerating analytics and AI use cases such as tailored LLMs and retrieval-augmented generation (RAG) to improve investigations and reduce analyst workload.

Amazon Neptune Integrates with Zep for Long-Term Memory

🧠 Amazon Web Services announced integration of Amazon Neptune with Zep, an open-source memory server for LLM applications, enabling persistent long-term memory and contextual history. Developers can use Neptune Database or Neptune Analytics as the graph store and Amazon OpenSearch as the text-search layer within Zep’s memory system. The integration enables graph-powered retrieval, multi-hop reasoning, and hybrid search across graph, vector, and keyword modalities, simplifying the creation of personalized, context-aware LLM agents.

Secure AI at Machine Speed: Full-Stack Enterprise Defense

🔒 CrowdStrike explains how widespread AI adoption expands the enterprise attack surface, exposing models, data pipelines, APIs, and autonomous agents to new adversary techniques. The post argues that legacy controls and fragmented tooling are insufficient and advocates for real-time, full‑stack protections. The Falcon platform is presented as a unified solution offering telemetry, lifecycle protection, GenAI-aware data loss prevention, and agent governance to detect, prevent, and remediate AI-related threats.

Cloudy-driven Email Detection Summaries and Guardrails

🛡️Cloudflare extended its AI agent Cloudy to generate clear, concise explanations for email security detections so SOC teams can understand why messages are blocked. Early LLM implementations produced dangerous hallucinations when asked to interpret complex, multi-model signals, so Cloudflare implemented a Retrieval-Augmented Generation approach and enriched contextual prompts to ground outputs. Testing shows these guardrails yield more reliable summaries, and a controlled beta will validate performance before wider rollout.