All news in category “AI and Security Pulse”

🔒 Agentic AI introduces a mounting Zero Trust challenge as autonomous agents increasingly act with inherited or unmanaged credentials, creating orphaned identities and ungoverned access. Ido Shlomo of Token Security argues that identity must be the root of trust and recommends applying the NIST AI RMF through an identity-driven Zero Trust lens. Organizations should discover and inventory agents, assign unique managed identities and owners, enforce intent-based least privilege, and apply lifecycle controls, monitoring, and governance to restore auditability and accountability.

⚠️ Researchers at SquareX demonstrated an AI Sidebar Spoofing attack that can overlay a counterfeit assistant in OpenAI's Atlas and Perplexity's Comet browsers. A malicious extension injects JavaScript to render a fake sidebar identical to the real UI and intercepts all interactions, leaving users unaware. SquareX showcased scenarios including cryptocurrency phishing, OAuth-based Gmail/Drive hijacks, and delivery of reverse-shell installation commands. The team reported the findings to vendors but received no response by publication.

🔐 The Hacker News is promoting a free webinar that presents a practical framework to secure AI at scale while preserving speed of adoption. Organizers warn of a growing “quiet crisis”: rapid proliferation of unmanaged AI agents and identities that lack lifecycle controls. The session focuses on embedding security by design, governing AI agents that behave like users, and stopping credential sprawl and privilege abuse from Day One. It is aimed at engineers, architects, and CISOs seeking to move from reactive firefighting to proactive enablement.

🛡️ This recap of the Agent Factory episode explains practical strategies for securing production AI agents, demonstrating attacks like prompt injection, invisible Unicode exploits, and vector DB context poisoning. It highlights Model Armor for pre- and post-inference filtering, sandboxed execution, network isolation, observability, and tool safeguards via the Agent Development Kit (ADK). The team demonstrates a secured DevOps assistant that blocks data-exfiltration attempts while preserving intended functionality and provides operational guidance on multi-agent authentication, least-privilege IAM, and compliance-ready logging.

📝 In many organizations the most consequential meeting attendee is the AI notetaker, whose summaries often become the authoritative meeting record. Participants can tailor their speech—using cue phrases, repetition, timing, and formulaic phrasing—to increase the chance their points appear in summaries, a behavior the author calls AI summarization optimization (AISO). These tactics mirror SEO-style optimization and exploit model tendencies to overweight early or summary-style content. Without governance and technical safeguards, summaries may misrepresent debate and confer an invisible advantage to those who game the system.

🤖 ChatGPT Atlas previews a future where AI becomes the primary interface for computing, letting users describe outcomes while the system orchestrates apps, data, and web services. Atlas demonstrates an context-aware assistant that understands a user’s digital life and can act on their behalf. This prototype points to productivity and accessibility gains, but it also creates new security, privacy, and governance challenges organizations must prepare for.

⚠️ Bruce Schneier highlights how facial recognition systems frequently fail people with nonstandard facial features, producing concrete barriers to services and daily technologies. Those interviewed report being denied access to public and financial services and encountering nonfunctional phone unlocking and social media filters. The author argues the root cause is often design choices by engineers who trained models on a narrow range of faces and calls for inclusive design plus accessible backup systems when biometric methods fail.

🔒 Since ChatGPT’s 2022 debut, enterprises have rapidly launched GenAI pilots but struggle to convert experimentation into measurable value — only 3 of 37 pilots succeed. The article identifies four critical bottlenecks: security & data privacy, observability, evaluation & migration readiness, and secure business integration. It recommends targeted controls such as confidential compute, fine‑grained agent permissions, distributed tracing and replay environments, continuous evaluation pipelines and dual‑run migrations, plus policy‑aware integrations and impact analytics to move pilots into reliable production.

🔒 DeepSeek collects extensive interaction data — chats, images and videos — plus account details, IP address and device/browser information, and retains it for an unspecified period under a vague “retain as long as needed” policy. The service operates under Chinese jurisdiction, so stored chats may be accessible to local authorities and have been observed on China Mobile servers. Users can disable model training in web and mobile Data settings, export or delete chats (export is web-only), or run the open-source model locally to avoid server-side retention, but local deployment and deletion have trade-offs and require device protections.

🧠 In episode 73 of The AI Fix, hosts Graham Cluley and Mark Stockley explore a sweep of recent AI developments, from the rise of AI-generated content to high-profile figures relying on chatbots. They discuss research suggesting Google Gemini exhibits behaviours resembling pathological gambling and report on a Gemma-style model uncovering a potential cancer therapy pathway. The show also highlights legal and security concerns— including a lawyer criticised for repeated AI use, generals consulting chatbots, and techniques for poisoning LLMs with only a few malicious samples.

🔐 AI promises stronger cyber defense but expands the attack surface if not governed properly. Organizations must secure models, data pipelines, and agentic systems with the same rigor applied to critical infrastructure. Identity is central: treat every model or autonomous agent as a first‑class identity with scoped credentials, strong authentication, and end‑to‑end audit logging. Adopt layered controls for access, data, deployment, inference, monitoring, and model integrity to mitigate threats such as prompt injection, model poisoning, and credential leakage.

🛡️ Check Point introduces a continuously trained AI engine that analyzes website content, structure, and authentication flows to detect phishing with high accuracy. Integrated with ThreatCloud AI, it delivers protection across Quantum gateways, Harmony Email, Endpoint, and Harmony Mobile. The model learns from millions of domains and real-time telemetry to adapt to new evasion techniques. Early results indicate improved detection of brand impersonation and credential-harvesting pages.

🛡️ Bruce Schneier and Barath Raghavan argue that agentic AIs run repeated OODA loops—Observe, Orient, Decide, Act—over web-scale, adversarial inputs, and that current architectures lack the integrity controls to handle untrusted observations. They show how prompt injection, dataset poisoning, stateful cache contamination, and tool-call vectors (e.g., MCP) let attackers embed malicious control into ordinary inputs. The essay warns that fixing hallucinations is insufficient: we need architectural integrity—semantic verification, privilege separation, and new trust boundaries—rather than surface patches.

📡 This recap of the Agent Factory podcast episode, hosted by Annie Wang with guest Ivan Nardini, explains how to evaluate autonomous agents using a practical, full-stack approach. It outlines what to measure — final outcomes, chain-of-thought, tool use, and memory — and contrasts measurement techniques: ground truth, LLM-as-a-judge, and human review. The post demonstrates a 5-step debugging loop using the Agent Development Kit (ADK) and describes how to scale evaluation to production with Vertex AI.

🔒 This article examines what ChatGPT collects, how OpenAI processes and stores user data, and the controls available to limit use for model training. It outlines region-specific policies (EEA/UK/Switzerland vs rest of world), the types of data gathered — from account and device details to prompts and uploads — and explains memory, Temporary Chats, connectors and app integrations. Practical steps cover disabling training, deleting memories and chats, managing connectors and Work with Apps, and securing accounts with strong passwords and multi-factor authentication.

🤖 OpenAI says GPT-6 will not ship in 2025 but continues to iterate on its existing models. The company currently defaults to GPT-5 Auto, which dynamically routes queries between more deliberative reasoning models and the faster GPT-5-instant variant. OpenAI has issued multiple updates to GPT-5 since launch. After viral analyst claims that GPT-6 would arrive by year-end, a pseudonymous OpenAI employee and company representatives denied those reports, leaving room for interim updates such as a potential GPT-5.5.

🔒 Generative AI and agentic systems are transforming phishing and smishing into precise, multilingual, and adaptive threats. What were once rudimentary scams now leverage large language models, voice cloning, and autonomous agents to craft personalized attacks at scale. For CISOs and security teams this represents a strategic inflection point that demands updated detection, user education, and cross-functional incident response.

🔐 Cybersecurity must evolve to meet rapid advances in agentic AI, quantum computing, low-code platforms and proliferating IoT endpoints. The author argues organizations should move from static defenses to adaptive, platform-based security that uses automation, continuous monitoring and AI-native protection to match attackers' speed. He urges early planning for post-quantum cryptography and closer collaboration with partners so security enables — rather than hinders — innovation.

⚠️ Enterprises now face a reality where autonomous AI agents run with system privileges, executing code and accessing sensitive data without human oversight. Fewer than 4 in 10 AI agents are governed by identity security policies, creating serious visibility and control gaps. Mature identity programs that use AI-driven identity controls and real-time data sync deliver stronger ROI, reduced risk, and operational efficiency. CISOs must move IAM from compliance checkbox to strategic enabler.

🔐AI-enabled attacks are rapidly shifting the threat landscape, with cybercriminals using deepfakes, automated phishing, and AI-generated malware to scale operations. According to Foundry's 2025 Security Priorities Study and CSO reporting, autonomous agents can execute full attack chains at machine speed, forcing defenders to adopt AI as a copilot backed by rigorous human oversight. Organizations are prioritizing human risk, verification protocols, and training to counter increasingly convincing AI-driven social engineering.