Jonathan Glass is a Cloud Security Director. The site already describes his work as AWS security architecture, DevSecOps, automation, and open source. This page does not add credentials, metrics, or a separate AI-security biography.
Each item is the publisher's title, publication date, and excerpt, and the link goes to the publisher's page. The generator does not write a paraphrase. A long excerpt is trimmed and marked. A feed with no matching item contributes nothing for that run.
MarkdownRSSAtomJSONJSON documentation
Sources
- AWS What's New — Amazon Bedrock, SageMaker, Amazon Q, and other generative-AI product announcements. Feed.
- AWS Machine Learning Blog — Posts that name Bedrock, SageMaker, or Amazon Q, or that discuss security of an AI system. Feed.
- AWS Security Blog — Security-blog posts that are about AI. Feed.
- OWASP GenAI Security Project — The project feed. Every entry is in scope. Feed.
- OWASP Top 10 for Large Language Model Applications — Release feed for the LLM Top 10 project. Feed.
- NIST News — NIST news whose title or opening text is about AI and security. Feed.
- NIST Cybersecurity Insights — NIST cybersecurity posts whose title or opening text is about AI and security. Feed.
- CISA Cybersecurity Advisories — Advisories whose title or opening text is about AI and security. Feed.
- CISA News — CISA news whose title or opening text is about AI and security. Feed.
- Microsoft Security Blog — Microsoft security posts that mention AI. Feed.
- Google Security Blog — Google security posts that mention AI. Feed.
- OpenAI News — OpenAI posts whose title is about cyber defense, vulnerabilities, prompt injection, or AI risk. Other product news is left out. Feed.
- UK NCSC — NCSC reports whose title or opening text is about AI and security. Feed.
A GitHub Actions workflow reads these feeds once a day. It needs no model API key. New URLs are added; stored items are not rewritten. The publication window for a newly fetched item is 400 days. Items already stored stay in the file.
Digest
- Full Fine-Tuning (FFT) on SageMaker AI Serverless Model Customization AWS Machine Learning Blog
Amazon SageMaker AI Serverless Model Customization now supports Full Fine-Tuning (FFT). This post explores when FFT outperforms LoRA across key benchmarks, examines the spectral properties of model weight matrices behind the quality gap, shares practical hyperparameter tuning guidelines, and shows how to get started.
- Connect Amazon Bedrock AgentCore Gateway to private APIs in a hub-and-spoke network with centralized inspection AWS Machine Learning Blog
Many enterprises run a centralized network model: one account owns every VPC and a central firewall inspects all traffic. This post shows a tested pattern for connecting Amazon Bedrock AgentCore Gateway to private APIs and MCP servers in that model, with the VPC Lattice resource gateway in the network account so every hop crosses the firewall.
- Design responsible AI controls for Amazon Aurora PostgreSQL AWS Machine Learning Blog
Learn how to make RAG chatbot answers traceable with Amazon Aurora PostgreSQL, pgvector, and Amazon Bedrock Guardrails, logging sources, scores, and guardrail traces in SQL.
- How Airbnb uses cost per task to operate coding agents on Amazon Bedrock AWS Machine Learning Blog
Airbnb runs evals on real engineering tasks and uses Amazon Bedrock observability to choose models for its coding agents and control production costs. This post shows how cost per task guides model selection, why production spending can differ from eval results, and how to monitor latency, manage quotas, and attribute spend.
- How Salesforce is advancing global-scale model serving with cross-Region inference routing in Amazon SageMaker AI AWS Machine Learning Blog
Learn how Salesforce uses the cross-Region inference router in Amazon SageMaker AI to turn fragmented Regional capacity into reliable model serving. Salesforce adds capacity securely across Regions and accounts while keeping its data residency commitments, and sees per request where each call was served and why.
- How Stretto built an AI voice agent with Amazon Nova 2 Sonic AWS Machine Learning Blog
Stretto replaced its web-form lead capture with Tara, an AI voice agent built on Amazon Nova 2 Sonic that conducts bankruptcy intake interviews by phone and qualifies leads. See how Stretto, the AWS Generative AI Innovation Center, and CI&T designed the voice architecture, validated it for sensitive conversations, and moved it to production.
- Introducing the Amazon SageMaker JumpStart Model Leaderboard AWS Machine Learning Blog
The Amazon SageMaker JumpStart Model Leaderboard compares 70+ foundation models side by side on quality, speed, and cost, directly in SageMaker Studio. Learn what the leaderboard shows, how AWS benchmarks models, and how to go from a shortlist to a deployed model.
- Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod AWS Machine Learning Blog
Large training jobs can stall or compute wrong results even when every node looks healthy. Amazon SageMaker HyperPod now adds workload recovery and expanded infrastructure checks that catch these failures sooner and raise the goodput of your training workloads.
- Private certificate authority support in Amazon Bedrock AgentCore Identity AWS Machine Learning Blog
Amazon Bedrock AgentCore Identity now supports private certificate authorities (CAs), so your agents can connect to self-hosted identity providers that use a private CA. This post shows how to issue an IdP certificate with AWS Private CA, configure a credential provider to trust it, rotate the CA, and protect the certificate.
- Amazon SageMaker AI now supports cross-Region inference routing AWS What's New
Today, Amazon SageMaker AI announces cross-Region inference routing, which helps keep inference applications available when a region runs short of capacity by sending requests to endpoints deployed in other AWS Regions and AWS accounts. Models served on accelerated instances can reach capacity limits in a single Region, and an unhealthy endpoint can lead to throttling and errors for end users. Previously, teams had to build and maintain their own routing, health checks, and...
- Amazon SageMaker HyperPod now supports higher pod density on EKS-orchestrated clusters AWS What's New
Amazon SageMaker HyperPod now supports higher pod density per node on EKS-orchestrated clusters, allowing you to get more out of every instance. This leaves more room for your applications alongside system DaemonSets for monitoring, logging, and security, and helps increase GPU, CPU and memory utilization on nodes, allowing you to run the same work using fewer instances. As you schedule more pods, the Amazon VPC CNI automatically adds network capacity to the node...
- Managing frontier AI risk: From training to deployment OpenAI News
OpenAI explains how it manages frontier AI risk from training through deployment with model alignment, sandboxing, blocking safeguards, and monitoring.
- Amazon SageMaker AI real-time endpoints now support KV cache aware routing AWS Machine Learning Blog
Amazon SageMaker AI real-time endpoints now support KV cache-aware routing, a new strategy that routes each request to the instance holding the longest cached match for its prompt. Learn how it works, when to use it compared with prefix-aware routing, and how to enable, invoke, and verify it on single model and inference component endpoints.
- Announcing AI data preparation capabilities in Amazon SageMaker: Build high-quality datasets for model development workflows AWS Machine Learning Blog
Amazon SageMaker AI now offers AI data preparation capabilities for building high-quality training and evaluation data. Generate synthetic examples, assess and improve datasets, auto-label at scale, and bring in expert review through Python SDK APIs and an agent skill, all from your own notebook or IDE.
- Cut generative AI costs: Code for rules, models for judgment AWS Machine Learning Blog
The biggest cost lever in a generative AI system is whether you call a model at all. Learn how to decide whether each workflow step needs a model, and map each option to AWS: deterministic code, a constrained decision call, or a right-sized model on Amazon Bedrock.
- Managed NVIDIA Dynamo on Amazon SageMaker HyperPod Inference AWS Machine Learning Blog
Amazon SageMaker HyperPod Inference now supports NVIDIA Dynamo for distributed inference, with multi-node and disaggregated serving, KV-aware routing, and automatic fault recovery. Serve large models across many nodes without building the orchestration layer yourself.
- Reducing token costs and latency in Amazon Bedrock AgentCore JSON workloads AWS Machine Learning Blog
As production agents on Amazon Bedrock AgentCore process multi-megabyte JSON payloads, token costs and latency climb. This post shares three composable strategies: offloading heavy artifacts to Amazon S3, on-demand result paging, and dictionary compaction. Together they cut per-turn token use by up to 71% and latency by up to 80%.
- Secure OAuth patterns for Snowflake Cortex AI through Amazon Bedrock AgentCore AWS Machine Learning Blog
When an AI agent on Amazon Bedrock AgentCore calls Snowflake Cortex AI over MCP, how does it authenticate? This post walks through three OAuth patterns we tested on AgentCore Identity: Snowflake OAuth, three-legged OAuth with a corporate IdP, and two-legged OAuth, so you can match your organization's identity, audit, and compliance needs.
- Securely exposing Amazon Bedrock AgentCore Runtime AWS Security Blog
Amazon Bedrock AgentCore Runtime delivers a secure serverless environment to deploy AI agents and tools at scale. When you start talking to your agent, the runtime launches a dedicated isolated session that runs in its own dedicated microVM with a completely sandboxed CPU, memory, and filesystem allocation. This provides strict data governance, helps to prevent […]
- Amazon Bedrock AgentCore Memory now provides full session summaries AWS What's New
Amazon Bedrock AgentCore Memory now keeps a full session summary for every session. It's a single record that gives a snapshot of what happened in the conversation. Summary chunks cover the conversation in more detail, while the full session summary captures the overall picture of where the session stands. AgentCore Memory updates it as new events arrive, so it always reflects the session so far. This works well for developers who want a quick recap rather than a...
- Amazon Bedrock AgentCore Memory now supports short-term memory retention of up to 10 years AWS What's New
Amazon Bedrock AgentCore Memory now lets you keep short-term memory events for up to 10 years, up from one year. Developers can now use short-term memory as a long-lived record of agent conversations and interactions. This helps when that history needs to stay available for a long time, such as for compliance and audit, for users who come back after months away, or for agents that need to look back at past sessions. You set retention on the memory resource, and it's applied...
- Amazon Bedrock AgentCore now offers free monthly web search queries AWS What's New
Amazon Bedrock AgentCore now offers 5,000 free web search queries per month through the Web Search Tool in AgentCore gateway and the Web Search API. AgentCore helps developers build, deploy, and operate highly effective agents securely at scale. Developers can now build and test agents with web search capabilities at no cost for their first 5,000 queries each month. The free allowance applies automatically, with no setup required. It is shared across supported AWS Regions...
- Amazon SageMaker HyperPod Inference now supports NVIDIA Dynamo for disaggregated and multi-node inference AWS What's New
Amazon SageMaker HyperPod Inference now supports NVIDIA Dynamo. You can now serve models that are too large for a single instance, and keep token generation fast when prompts are long. You don't have to build or operate distributed serving infrastructure yourself. HyperPod manages Dynamo for you through the Inference Operator add-on. As models grow, two problems limit inference. A large model can need more GPU memory than one instance has. Long prompts also slow token...
- Amazon SageMaker HyperPod now supports cluster operations for tracking scaling and on-demand Deep Health Check requests AWS What's New
Amazon SageMaker HyperPod introduces cluster operations, giving you visibility into every scaling and on-demand deep health check request from submission to completion. When a request runs into errors, the SageMaker AI console shows an alert that links directly to that request's error events. With continuous provisioning, HyperPod brings capacity online in the background as it becomes available, retries failed nodes automatically, and lets you run multiple scaling requests...
- Amazon SageMaker now supports AI data preparation capabilities to build high-quality datasets for model development AWS What's New
Building high-quality training datasets has traditionally required weeks of manual labeling and data cleaning. Amazon SageMaker now offers AI data preparation capabilities that help data scientists and ML engineers build high-quality training and evaluation datasets for both text-based model customization and traditional ML. Teams can generate synthetic examples grounded in their own documents, auto-label records at scale with confidence scores, incorporate expert feedback...
- OpenAI GPT-6.2 Astra, and GPT-6.2 Sol are now generally available on Amazon Bedrock AWS What's New
Today, AWS announces the general availability of OpenAI GPT-6.2 Astra and GPT-6.2 Sol on Amazon Bedrock. GPT-6.2 Astra brings frontier-level reasoning and judgment to your most ambitious work, including complex business problems, demanding research, and advanced coding and agentic workflows. Astra also includes an Ultrafast mode for latency-sensitive applications that need fast responses. GPT-6.2 Sol is designed for recurring coding, agentic, and professional workflows with...
- Security for the agentic era, powered by Microsoft Perception Microsoft Security Blog
Read about updates to Microsoft Perception and the new Microsoft Security cyber stack to defend against threats, secure agents, and protect your digital estate. The post Security for the agentic era, powered by Microsoft Perception appeared first on Microsoft Security Blog.
- The risks of device code authentication for AI coding agents Microsoft Security Blog
Lab research shows how device code phishing, a technique that applies to any device-flow client, can extend to AI coding agents, using GitHub Copilot CLI as an illustrative example. The post The risks of device code authentication for AI coding agents appeared first on Microsoft Security Blog.
- Strengthening NATO and allied cyber defenses with AI OpenAI News
How OpenAI is working with NATO and allied cyber agencies to help trusted defenders find vulnerabilities, test fixes and protect essential systems.
- Amazon SageMaker AI now supports KV cache-aware routing for real-time inference endpoints AWS What's New
Amazon SageMaker AI now supports KV cache-aware routing for real-time inference endpoints, enabling you to reduce time to first token for LLM workloads with long or repeated prompts. Serving engines such as vLLM store the computed key-value (KV) cache for repeated prompt starts such as shared system prompts, documents, and conversation history, to skip repeated work. Across several instances, a request that lands where the cache is missing recomputes it. Under high load...
- Amazon Threat Intelligence observes threat actors running cybercrime campaigns with ARTEX AI agents AWS Security Blog
From Oct. 3 to Nov. 5, 2026, Amazon’s MadPot, a globally distributed network of decoy threat sensors, captured requests from AI agents that included operating memory from offensive campaigns that threat actors ran on ARTEX, an open-source agentic AI penetration testing framework. The ARTEX agents sent these requests to MadPot sensors configured to present as […]
- Detecting sleeper agents hiding in AI model neurons Microsoft Security Blog
Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than ten neurons to inject a short payload; Microsoft Research has also found that this threat is detectable by frontier agents, which can identify anomalous weight edits. The post Detecting sleeper agents hiding in AI model neurons appeared first on Microsoft Security Blog.
- Cogent and OpenAI build cyber defense factories for enterprises OpenAI News
Cogent combines OpenAI models with enterprise context to help automatically remediate vulnerabilities with agents.
- Help defend against memory poisoning in Amazon Bedrock AgentCore with multi-layer write validation AWS Security Blog
Amazon Bedrock AgentCore Memory helps AI agents maintain context across sessions through persistent short-term and long-term memory. Because memory content is automatically retrieved and injected into future conversations, the integrity of what gets written to memory directly shapes future agent behavior, which makes the write path a valuable control point to strengthen. AgentCore already provides […]
- FORGE Lab uses agentic tools to identify memory safety issues in Rust Microsoft Security Blog
Microsoft FORGE Lab researchers found memory-safety bugs in Rust's core and std libraries, including cases where safe Rust code can trigger undefined behavior. Using Hyenas, FORGE's frontier research version of codename MDASH, the team investigated three patterns of misplaced trust in unsafe code and what they reveal about Rust's safety guarantees. The post FORGE Lab uses agentic tools to identify memory safety issues in Rust appeared first on Microsoft Security Blog.
- ARTEX abuse expands as cybercriminals target financial sector Microsoft Security Blog
In October 2026, the financially motivated threat actor Storm-3358 began targeting organizations in the financial sector using the agentic AI offensive framework ARTEX. The post ARTEX abuse expands as cybercriminals target financial sector appeared first on Microsoft Security Blog.
- Partnering with Hacktron to find vulnerabilities in OpenAI’s systems OpenAI News
OpenAI is partnering with Hacktron to find vulnerabilities, test connections with third-party services, and strengthen defenses with frontier AI.
- GPT‑6 Cyber: Advancing the frontier of aligned cybersecurity agents OpenAI News
Introducing GPT‑6 Cyber, OpenAI’s cybersecurity model for finding exploitable vulnerabilities and developing fixes, trained to stay within authorized scope.
- Artificial intelligence and cyber intrusion UK NCSC
An NCSC assessment that examines current AI-enabled threat trends and projections of the threat landscape to 2028.
- Preparing our next security sprint to harden OpenAI OpenAI News
OpenAI is preparing its next internal security sprint with Cathedral Systems to test and strengthen its defenses using AI.
- Design Tenets for Agent Identity Management Systems NIST Cybersecurity Insights
This is blog #2 in our series on agentic identity, authentication and authorization. Our other post can be found via Post #1. In our last blog post, we highlighted the essential nature of having fundamentally sound identity and access management (IAM) capabilities as a precursor to implementing agents at scale. We started to form the core of what “good looks like” but wanted to take this a step further by defining an initial set of “Design Tenets” for agentic identity...
- How Check Point accelerates vulnerability research with Daybreak OpenAI News
With OpenAI Daybreak, Check Point speeds up the research behind new security protections, enabling its analysts to turn vulnerability intelligence into customer defenses faster.
- Cloudflare links vulnerability discovery to defense with OpenAI OpenAI News
Cloudflare uses OpenAI Daybreak to investigate vulnerabilities and propose fixes for review. Its developers use Codex to build faster and improve code quality.
- Democratic governance of frontier AI, part II: Empowering cyber defenders OpenAI News
OpenAI outlines a blueprint for empowering cyber defenders with frontier AI, stronger safeguards, modernized cybersecurity, and more resilient public institutions.
- Patch the Planet: global response coordination as agents uncover critical vulnerabilities OpenAI News
Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities across open source.
- Sophos cuts threat investigation time by 96% with OpenAI Daybreak OpenAI News
Discover how Sophos uses OpenAI’s Daybreak to cut cyber-threat investigation time by 96% and automate 52% of MDR cases while preserving human oversight.
- GenAI and Agentic AI Exploit Roundup Q3 2026 OWASP GenAI Security Project
Coverage period: July 1, 2026 through September 30, 2026 Overview This roundup consolidates selected major AI-related security incidents and exploit disclosures reported during the coverage period. It aligns each entry to the OWASP Top 10 for LLM Applications 2026 and the OWASP Top 10 for Agentic Applications 2026, with published CVE references where available. It […] The post GenAI and Agentic AI Exploit Roundup Q3 2026 appeared first on OWASP Gen AI Security Project.
- Towards safety cases for frontier AI training OpenAI News
Our early guidelines for safety cases in frontier AI training cover technical safeguards, operational practices, and investigating misalignment incidents
- OpenAI extends cyber access to Ukraine for civilian defense OpenAI News
OpenAI is extending access to its Daybreak program to the Government of Ukraine to support the cyber defense of civilian infrastructure.
- Expanding AI access and cyber defense for federal, state, local, and tribal governments OpenAI News
OpenAI and GSA will offer eligible federal, state, local, and tribal governments $0 license fees, 50% off usage, and expanded cyber defense support.
- OWASP GenAI Security Project Unveils 2026 Top 10 for LLM Applications, New Agent Control Standard and Sponsors as Community Tops 30,000 Members OWASP GenAI Security Project
OWASP GenAI Security Project Releases 2026 Top 10 for LLM Applications, Debuts Agent Control Standard and New Resources for Securing Generative and Agentic AI F5, WitnessAI, Evoke Security and Mondoo Inc. join as new sponsors as community expands AI security solutions guidance and surpasses 30,000 members WILMINGTON, Del. — Sept. 2, 2026 — The OWASP […] The post OWASP GenAI Security Project Unveils 2026 Top 10 for LLM Applications, New Agent Control Standard and Sponsors as...
- Path to Astra: critical capabilities and frontier safeguards OpenAI News
Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.
- Back to the Future: Why Agentic AI Needs a Strong Identity Foundation NIST Cybersecurity Insights
As AI matures, enterprises and customers are rapidly deploying agents seeking to unlock the next level of automation and productivity. Agentic AI shows potential to handle a multitude of use cases, from buying personal items on Amazon to customer service applications to enterprise security and software development. However, early agentic deployments are repeating a familiar pattern: prioritizing feature development and immediate value over security. This strategy is...
- Pacing model development in an era of cyber-critical capabilities OpenAI News
OpenAI is strengthening monitoring, alignment, and security for frontier AI models. See how new safeguards are guiding the pace of model development.
- Shaping the NVD for the Future: We Need Your Feedback on AI-Enabled Vulnerability Management NIST Cybersecurity Insights
For over two decades, the NIST National Vulnerability Database (NVD) has served as the U.S. government repository for standards-based vulnerability management data and as a foundational resource for cybersecurity risk analysis, vulnerability management, compliance automation, and software security. New Opportunities for the NVD via Automation Our cybersecurity landscape is changing dramatically and is being reconfigured by artificial intelligence (AI) in unique, exciting...
- Expanding Daybreak as the Cyber Defense Window Narrows OpenAI News
Meet GPT-5.6-Cyber, OpenAI’s cybersecurity-specific model available through Daybreak Red for authorized vulnerability research, exploit validation, and security testing.
- Putting frontier cyber models in more trusted hands OpenAI News
Approved Daybreak partners can use OpenAI’s frontier cyber models to deliver authorized, governed cybersecurity services to customers.
- Responding to the next frontier of critical cyber capabilities OpenAI News
OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.
- Third-party cyber evaluations involving OpenAI models OpenAI News
OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.
- GenAI and Agentic AI Exploit Roundup Q2 2026 OWASP GenAI Security Project
April 1 through June 30 2026 Overview Six selected cases show how AI integrations, coding tools, and browser agents can turn ordinary inputs or delegated access into security exposure. Defenders should constrain tool execution and credentials, preserve input provenance, and monitor the actions agents take. Coverage includes incidents and technical disclosures published during the quarter. […] The post GenAI and Agentic AI Exploit Roundup Q2 2026 appeared first on OWASP Gen...
- NIST Mathematical Proof Supports Transition to a Continuous-Monitor-and-Update Security Model for AI Systems NIST News
The proof extends to AI the logic used by famed mathematician Kurt Gödel, whose incompleteness theorems have had a profound effect on math for nearly a century.
- Election information and safeguards in 2026 OpenAI News
Learn how OpenAI is supporting elections in 2026 through reliable information, cyber defense, AI transparency, misuse safeguards, and bias monitoring.
- Memory Is a Feature. It Is Also an Attack Surface OWASP GenAI Security Project
As co-lead of OWASP ASI06: Memory & Context Poisoning entry as part of OWASP Top 10 for Agentic Applications , I have spent a lot of time thinking about a simple question: what happens when an AI agent does not just process untrusted input, but carries it forward? That is the core issue behind ASI06. […] The post Memory Is a Feature. It Is Also an Attack Surface appeared first on OWASP Gen AI Security Project.
- Scaling Trusted Access for Cyber with GPT-5.5 and GPT-5.5-Cyber OpenAI News
OpenAI expands Trusted Access for Cyber with GPT-5.5 and GPT-5.5-Cyber, helping verified defenders accelerate vulnerability research and protect critical infrastructure.
- Cybersecurity in the Intelligence Age OpenAI News
OpenAI outlines a five-part action plan for strengthening cybersecurity in the Intelligence Age, focused on democratizing AI-powered cyber defense and protecting critical systems.
- AI threats in the wild: The current state of prompt injections on the web Google Security Blog
Posted by Thomas Brunner, Yu-Han Liu, Moni Pande At Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now, Indirect Prompt Injection (IPI) is a top priority for the security community, anticipating it as a primary attack vector for adversaries to target and compromise AI agents. But while the danger of IPI is widely discussed, are threat actors...
- Accelerating the cyber defense ecosystem that protects us all OpenAI News
Leading security firms and enterprises join OpenAI’s Trusted Access for Cyber, using GPT-5.4-Cyber and $10M in API grants to strengthen global cyber defense.
- FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project OWASP GenAI Security Project
FinBot is a hands-on companion to the OWASP GenAI Security Project, offering an interactive Capture-The-Flag environment built around a simulated financial services application. Designed as the 'Juice Shop for the Agentic AI', it lets builders and defenders explore agentic risks in a live, multi-agent system with real tool access. The post FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project appeared first on OWASP Gen AI Security Project.
- OWASP GenAI Exploit Round-up Report Q1 2026 OWASP GenAI Security Project
OWASP GenAI Exploit Round-up Report Q1 2026 Coverage period: January 1, 2026 through April 11, 2026 Overview For the last two years the OWASP GenAI Security Project published a list of the major incidents for the last quarter. This is not designed to be an exhaustive report. This report consolidates major AI-related security incidents and […] The post OWASP GenAI Exploit Round-up Report Q1 2026 appeared first on OWASP Gen AI Security Project.
- Trusted access for the next era of cyber defense OpenAI News
OpenAI expands its Trusted Access for Cyber program, introducing GPT-5.4-Cyber to vetted defenders and strengthening safeguards as AI cybersecurity capabilities advance.
- CyberAgent moves faster with ChatGPT Enterprise and Codex OpenAI News
CyberAgent uses ChatGPT Enterprise and Codex to securely scale AI adoption, improve quality, and accelerate decisions across advertising, media, and gaming.
- Google Workspace’s continuous approach to mitigating indirect prompt injections Google Security Blog
Posted by Adam Gavish, Google GenAI Security Team Indirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by the LLM as it completes the user’s query. This may even be possible without any input directly from the user. IPI is not the...
- Reflections from the Second NIST Cyber AI Profile Workshop NIST Cybersecurity Insights
Thank you to everyone who participated in the Cybersecurity Framework Profile for Artificial Intelligence (Cyber AI Profile) Workshop in January! The input we received on the Preliminary Draft during this workshop has been invaluable and is informing the development of the next draft of the NIST Cyber AI Profile. We are working toward publishing a full workshop summary soon that captures themes and highlights from the event. In the interim, we would like to share a preview...
- OWASP GenAI Security Project Expands AI Security Frameworks Ahead of RSA 2026, Celebrates Continued Sponsor Support OWASP GenAI Security Project
New resources, a full week of RSA programming and growing industry adoption mark a milestone moment for the open-source AI security community WILMINGTON, Del. — March 19, 2026 — The OWASP GenAI Security Project (genai.owasp.org), a leading global open-source and expert community, growing to more than 25K members, dedicated to delivering practical guidance and tools […] The post OWASP GenAI Security Project Expands AI Security Frameworks Ahead of RSA 2026, Celebrates...
- Designing AI agents to resist prompt injection OpenAI News
How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.
- Announcing the "AI Agent Standards Initiative" for Interoperable and Secure Innovation NIST News
The Initiative will ensure that the next generation of AI is widely adopted with confidence, can function securely on behalf of its users, and can interoperate smoothly across the digital ecosystem.
- Introducing Trusted Access for Cyber OpenAI News
OpenAI introduces Trusted Access for Cyber, a trust-based framework that expands access to frontier cyber capabilities while strengthening safeguards against misuse.
- “Cyber Special Operations”: China-linked influence planning OpenAI News
OpenAI banned an account linked to an individual associated with Chinese law enforcement, using AI to plan influence activity, harassment, and online operations.
- Continuously hardening ChatGPT Atlas against prompt injection OpenAI News
OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning. This proactive discover-and-patch loop helps identify novel exploits early and harden the browser agent’s defenses as AI becomes more agentic.
- Evolving AI Transparency: The Journey of the AIBOM Generator and Its New Home at OWASP OWASP GenAI Security Project
Earlier this year, during RSAC 2025, we introduced something the industry had never seen before: an open-source tool capable of generating an AI Software Bill of Materials (AIBOM) for models on Hugging Face. That launch ignited a wave of interest across the security, AI, and software supply chain communities. It confirmed what many of us […] The post Evolving AI Transparency: The Journey of the AIBOM Generator and Its New Home at OWASP appeared first on OWASP Gen AI Security...
- OWASP GenAI Security Project Releases Top 10 Risks and Mitigations for Agentic AI Security OWASP GenAI Security Project
Culmination of over 100 industry leaders’ input and extensive published resources to deliver critical guidance to address Agentic AI Security risks WILMINGTON, Del. — Dec. 10, 2025 — The OWASP GenAI Security Project (genai.owasp.org), a leading global open-source and expert community dedicated to delivering practical guidance and tools for securing generative and agentic AI, […] The post OWASP GenAI Security Project Releases Top 10 Risks and Mitigations for Agentic AI...
- OWASP Top 10 for Agentic Applications – The Benchmark for Agentic Security in the Age of Autonomous AI OWASP GenAI Security Project
Introducing the OWASP Top 10 for Agentic AI Applications - our community’s actionable framework for securing autonomous, tool-using AI systems. Built at global scale informed by real incidents, and based on our work already adopted across industry, this release marks a pivotal moment in turning insight into action, and advancing the security of Agentic Applications at the pace of innovation. The post OWASP Top 10 for Agentic Applications – The Benchmark for Agentic Security...
- Strengthening cyber resilience as AI capabilities advance OpenAI News
OpenAI is investing in stronger safeguards and defensive capabilities as AI models become more powerful in cybersecurity. We explain how we assess risk, limit misuse, and work with the security community to strengthen cyber resilience.
- Architecting Security for Agentic Capabilities in Chrome Google Security Blog
Posted by Nathan Parker, Chrome security team Chrome has been advancing the web’s security for well over 15 years, and we’re committed to meeting new challenges and opportunities with AI. Billions of people trust Chrome to keep them safe by default, and this is a responsibility we take seriously. Following the recent launch of Gemini in Chrome and the preview of agentic capabilities, we want to share our approach and some new innovations to improve the safety of agentic...
- Understanding prompt injections: a frontier security challenge OpenAI News
Prompt injections are a frontier security challenge for AI systems. Learn how these attacks work and how OpenAI is advancing research, training models, and building safeguards for users.
- Introducing gpt-oss-safeguard OpenAI News
OpenAI introduces gpt-oss-safeguard—open-weight reasoning models for safety classification that let developers apply and iterate on custom policies.
- gpt-oss-safeguard technical report OpenAI News
gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using the underlying gpt-oss models as a baseline. For more information about the development and architecture of the underlying...