ShieldFont Poisons AI Training Data by Swapping Words While Preserving Grammar
ShieldFont, a free font created by Brazilian agency Seneda & Abrucio and Danish studio Playtype, offers website owners a new way to disrupt unauthorized collection of text for training generative AI models.
Publishing content online now exposes material not only to human readers but also to AI scrapers that frequently ignore robots.txt directives. ShieldFont counters this by allowing scrapers to access the page while feeding them deliberately altered text that remains grammatically plausible.
The font leverages the OpenType mechanism for glyph substitution, replacing entire words rather than individual characters. Nouns are swapped with nouns, past-tense verbs with past-tense verbs, and plural forms are preserved. The vocabulary is organized into 250 groups based on parts of speech and semantic features, resulting in roughly one quarter of words being altered while maintaining readable structure.
This controlled substitution aims to keep poisoned text inside training datasets instead of being filtered out by quality checks. When evaluated with FineWeb-Edu, about 10 percent of fragments previously rated as high quality still passed after protection, yet 55.8 percent of tested excerpts contained facts that no longer matched the original.
ShieldFont is not immune to all extraction methods. Screenshots followed by OCR can recover the original text, and screen readers for visually impaired users currently read the substituted words. Developers have added a beta feature to supply the correct text to assistive technologies, though accessibility concerns remain unresolved.
The font currently supports only English and is freely available on GitHub.
Related articles
Thousands of Grok-Generated Apps Expose Sensitive Corporate Data Through Default Public Access
Security firm Claroc scanned 43,551 Grok-built application addresses and found 37,571 still online, with 94.7 percent requiring no login. Approximately 650 to 800 of these apps contained sensitive internal data belonging to SpaceX, X, Tesla, and 30 other organizations, including six Fortune 500 companies. Exposed records included ICU patient reports with lab results and ventilator status, contractor timesheets containing plaintext passwords, and Tesla service-center performance evaluations listing employee names, efficiency metrics, and bonuses. Researchers demonstrated that Grok sometimes inverts permission-check logic, allowing unauthorized Google accounts to view and modify data after login. In contrast, ChatGPT-generated apps default to private settings, preventing access even when URLs are discovered via passive DNS. The incident highlights how AI coding tools lower the barrier to publishing internal applications while weakening the review processes that traditionally protected sensitive data.
Enterprise Security Requirements Push Russian Developer to Deploy 125B MoE LLM Locally on Consumer Hardware
A cybersecurity journalist and platform developer detailed his transition from cloud-based AI agents to a fully local 125B-parameter MoE model after enterprise clients raised strict data-exfiltration concerns. The move was driven by the need to keep task statements, source code, configuration files, logs, and regulated personal data inside the corporate perimeter. After testing multiple inference engines, he settled on the Strata engine running a Qwen3.8-Flash-Next model quantized to IQ3_S, achieving 22-25 tokens per second generation and over 500 tokens per second prefill on an RTX 5060 Ti 16 GB GPU paired with a Xeon E5-2640 v3 and 128 GB DDR4. Extensive calibration of expert caching, PCIe fraction, KV streaming, and speculative decoding proved critical to reaching production-grade performance. The resulting setup now handles real agentic workloads such as incident investigation from traces, backlog grooming, and code generation without any data leaving the workstation. The author concludes that hybrid cloud-local workflows will become standard for development teams handling sensitive information within the next one to two years.
VK Tech Releases Offline-Capable VK AI Space 26.3 for Secure Enterprise AI Agents
VK Tech has launched version 26.3 of its corporate AI platform VK AI Space, enabling organizations to deploy generative AI agents that operate entirely without internet access. The update integrates seven modules for model connectivity, knowledge base management, and multi-agent orchestration while supporting full on-premises installation on customer hardware. Key security controls include role-based access management, usage quotas, comprehensive audit logging, and configurable checkpoints that pause agent actions for human approval when required. Agents can interact with internal APIs, databases, and file systems through multi-step workflows, with built-in validation against test datasets and restrictions on tool usage. The platform also provides multi-level memory, ready-to-use component libraries, and hooks for fine-tuning agent behavior. VK Tech confirmed that version 26.3 successfully passed testing under an approved program that specifically verified operation in air-gapped environments.
AI Coding Assistants Generate Insecure Code and Amplify Supply-Chain Risks in Production
A detailed analysis of AI coding assistants reveals that generated code contains vulnerabilities in 45% of cases according to Veracode research, with models frequently choosing unsafe options for log injection and XSS. Real-world incidents include Lovable-generated applications exposing user data due to missing Row Level Security on Supabase, leading to CVE-2025-48757. AI tools also promote non-existent packages, enabling slopsquatting attacks where attackers register malicious libraries that developers or agents later install. Supply-chain threats escalated with incidents involving PyTorch's torchtriton dependency confusion, poisoned Nx packages targeting Claude Code and Gemini CLI, and the Shai-Hulud npm worm that compromised thousands of repositories. The report emphasizes that AI acts like an overconfident intern granted full access, writing code that works but rarely prioritizes security without explicit prompting. Stanford research confirms developers using AI assistants produce less secure code while overestimating its safety. Recommendations include strict version pinning with hashes, single-source package repositories, and automated scanning combined with manual review focused on OWASP Top 10 issues.