All news in category “AI and Security Pulse”

🔒 Microsoft announced new controls to contain agentic AI workloads, including the Microsoft Execution Container (MXC) runtime and enhancements to the multi-agent vulnerability research system MDASH. MXC is a policy-driven sandbox for specifying and enforcing access to files, networks, credentials, and resources at runtime across Windows, Linux, and macOS. The company also highlighted Agent 365 SDK, Windows 365 for Agents, and two open-source standards—ASSERT and Agent Control Specifications—to govern agent behavior across platforms.

🔒 The rapid rise of frontier and agentic AI is creating board-level urgency that may finally unlock sustained cybersecurity funding. Industry leaders at recent conferences noted that autonomous AI systems expose operational risk, widen attack surfaces, and outpace traditional security architectures. CISOs are reframing cybersecurity as an operational enabler for safe AI adoption, pushing for investments in visibility, identity, monitoring, and AI-specific controls. Vendors and experts caution that budget requests need clear business cases tied to measurable outcomes.

🛡️ Anthropic has broadened Project Glasswing, giving 150 additional organizations access to its most capable model, Claude Mythos Preview, to help find vulnerabilities in critical software. The program, first opened to roughly 50 partners in April, claims more than 10,000 high- or critical-severity flaws discovered to date. New participants span 15+ countries and underrepresented sectors like power, water, healthcare and hardware, chosen for the potential catastrophic impact of breaches. Anthropic warned that while discovery is accelerating, safe public release of Mythos-class models remains restricted due to incomplete safeguards.

🔍 Halcyon research reveals a dramatic rise in AI-powered cybercrime tooling across underground markets, jumping from 38 mentions in December to 1,486 in February. Cynthia Kaiser, SVP of Halcyon’s Ransomware Research Center, detailed four product categories: weaponized LLMs, AI-enabled identity fraud, AI-augmented malware/infrastructure, and jailbroken or stolen AI services. She warned that automated distribution, freemium models and redundant channels have lowered the financial barrier to entry and increased resilience against takedown efforts.

🔎 Anthropic has added 150 additional companies to its Project Glasswing initiative, prioritizing critical infrastructure sectors like power, water, healthcare, communications, and hardware. Analysts view the expansion positively for increasing vulnerability discovery, but warn of a remediation bottleneck: vendors and SOCs may struggle to validate, prioritize, and patch a potential 10x or greater increase in findings. Experts emphasize the need for confidence scoring, automation, and third-party validation to maintain trust and ensure timely remediation.

🔒 Reporting suggests attackers used Meta’s AI support chatbot to change recovery emails on high-profile Instagram accounts, leading to notable takeovers. The core issue isn’t just prompt injection or a model jailbreak but that the AI operated within a sensitive account recovery workflow with insufficient independent verification. Organizations must treat AI-driven support actions as part of the security boundary and constrain authority, permissions, and verification around such agents.

🧭 Microsoft announces the general availability of Microsoft Discovery, a platform for building and governing agentic AI workflows tailored to scientific and engineering R&D. The release includes a preview of the Microsoft Discovery app, a local desktop experience for researchers and small teams to explore hypotheses, literature, and iterative experimentation. The platform emphasizes evidence preservation, traceability, governance, and integration with existing tools and institutional data to support repeatable, transparent scientific workflows.

🛡️ Joe Slowik warned at Infosecurity Europe that defenders must adopt AI to keep pace with adversaries. He argued that purely human-driven SOCs cannot match the accelerated timescales enabled by AI, ML and LLMs, leaving organisations exposed. Slowik recommended rethinking security operations to integrate AI agents for rapid intelligence, enrichment and remediation, while keeping humans in the decision loop. He used the React2Shell example to illustrate the speed of modern exploits.

🧭 At Infosecurity Europe 2026, Bayer CISO Kevin Jones outlined a shift from checklist-based guidance to psychology-first security awareness to counter AI-enabled social engineering. The firm mandates behavior-focused training, ties AI access to role-based modules, and gates agent development behind completion. Bayer is moving SOCs toward supervised automation and updating supplier contracts and governance to enforce AI transparency and controls.

🔒 Bruce Schneier reflects on his 2010 Dark Reading essay arguing that while cryptography provides strong mathematical advantages, it cannot by itself secure modern, interconnected systems. He traces how crypto has been applied since the 1990s and explains that computer security is an ongoing arms race of fragile defenses. Schneier warns that AI changes the landscape by automating vulnerability discovery and exploit creation, shifting the balance between attackers and defenders.

🧩Trustpilot built a high-volume streaming pipeline using fine-tuned Gemma models to process millions of user reviews in near real-time under tight latency and cost constraints. The team replaced variable per-token pricing with fixed infrastructure costs, fine-tuned lightweight models for tasks like NER, sentiment, and topic classification, and separated classifier and LLM endpoints. Performance tuning, vLLM optimizations, and load testing enabled scalable inference despite challenges with private networking, deployment observability, and GPU availability.

🛡️ Vendors at Infosecurity Europe 2026 agree that AI will not eliminate security operations centers but will automate repetitive triage and ticketing. Experts urge treating AI as a glass box, ensuring transparency and human-in-the-loop validation. The shift accelerates junior analysts into supervisory tier-1.5 roles and creates demand for cyber defense engineers who build and tune detection systems.

🧭 At Infosecurity Europe 2026, OWASP will unveil the Agentic Research Council to better align fast‑moving agentic AI capabilities with security research and operational practice. Launched from the GenAI Security Project’s Agentic Security Initiative, the council will prioritize a public research pipeline, convene working groups and connect academic outputs to deployable mitigations. The initiative aims to accelerate runtime‑focused defenses against multi‑agent threats.

🛡️ Cybersecurity researchers disclosed a vulnerability dubbed ChatGPhish that exploits ChatGPT's trust in Markdown links and images to perform prompt injections and enable phishing. The flaw causes the assistant to auto-fetch attacker-hosted images and render malicious links and QR codes inside the trusted UI, potentially leaking client metadata like IP and User-Agent. The technique highlights summarization as an adversarial surface that can convert benign web pages into phishing vectors.

🛰️ The Linux Foundation has proposed DNS-AID, a standards-driven extension to the Domain Name System to let AI agents discover, verify, and communicate without new infrastructure. The project leverages a well-known DNS address pattern (for example, _index._agents.{domain}) to provide a global, vendor-neutral directory for agents and MCP servers. Initial work was done by Infoblox, with contributions from Deutsche Telekom and Amazon, and the foundation is soliciting further input to keep the approach scalable and secure.

🔬 Researchers at ETH Zurich report creating a device that generates provably perfect random numbers using two superconducting qubits, a 30-meter microwave guide, and specialized software. The setup leverages quantum entanglement and an amplification algorithm to remove bias common in classical and many quantum sources. The team says the output can be certified and could serve cryptographic key generation or public randomness services.

🚀 Claude Opus 4.8 is now accessible in Microsoft Foundry, providing developers and enterprises with Anthropic’s most capable Opus model for coding, agentic tasks, and professional work. The update focuses on long-running workflows, deeper reasoning across documents and codebases, and more reliable tool use for multi-step automation. Teams can now evaluate and deploy the model within Foundry’s unified platform for building and operating AI applications.

🤖 Anthropic confirmed plans to release its Mythos-class AI models to the general public after previously restricting access because of security risks to public and private software. Initially available only to select organizations and researchers, Mythos was held back while Anthropic developed stronger safeguards. The company says it’s making swift progress and expects to offer Mythos-class models to customers in the coming weeks, noting significant gains in code reasoning and autonomy over its Opus 4.8 flagship.

🧭 This collaboration between Google Public Sector and the University of Central Oklahoma (UCO) Forensic Science Institute uses Google’s NotebookLM to rapidly analyze complex criminal case documents and construct timelines. Originating from an AI hackathon co-led by UCO’s CIO Sonya Watkins, the project leverages Gemini to prioritize high-impact prototypes and has reduced multi-month analyses to days in early trials. UCO instructors ensure AI outputs are forensically sound and reliably cited.

🖼️ Google Cloud announced Nano Banana 2 (Gemini 3.1 Flash Image) and Nano Banana Pro (Gemini 3 Pro Image) are generally available via the Gemini Enterprise Agent Platform, offering enterprise-grade image generation and editing. Nano Banana 2 now supports video files as input in preview, enabling deep video understanding to generate context-aware images. 1K and 2K outputs are GA while 4K remains in preview. The models are integrated by partners like Adobe, WPP, Shopify, URBN, and Magnopus to scale creative workflows and production pipelines.