Every successful jailbreak prompt has a price. A look at the underground market for AI agent bypasses in 2026 — who builds them, who buys them, and how the profit motive shapes the threat landscape.
Martynas Vareikis
Martynas Vareikis
Martynas Vareikis is the AI Editor at Ransomnews. He covers the intersection of artificial intelligence and information security — from machine-learning models in defensive tooling to the adversarial use of LLMs by ransomware operators, deepfake-driven social engineering, and the rise of agentic threats. His reporting focuses on translating fast-moving AI research into practical guidance for defenders, journalists, and the broader security community. Reach Martynas via [email protected].
Running models locally feels safer than sending data to OpenAI. Sometimes it is. Sometimes it isn’t. A practitioner’s breakdown of the actual security trade-offs between local and cloud AI deployments.
AI in security operations has graduated from vendor demoware to production reality — but only in three specific use cases. Here’s where AI is genuinely changing SOC work in 2026, and where it still doesn’t.
A practitioner’s account of building a local AI stack with OpenClaw — and discovering that out-of-the-box defaults turn it into a wide-open data exposure surface for prompt injection and remote compromise.
The EU AI Act, in force since August 2024 and phasing in through 2027, is the first comprehensive AI regulation in any major jurisdiction. Here is what it actually requires, who it applies to, and what organisations should be doing now.
Red teaming for traditional software is well-defined. Red teaming for AI systems borrows the term but operates differently. Here is what AI red teaming actually involves, the documented methodologies, and how to structure an effective exercise.
Should you build on a closed API like GPT-5 or Claude, or run an open-weight model like Llama 4 or Mistral on your own infrastructure? The choice has real security implications that go beyond cost and performance.
A trained model represents enormous investment in compute, data, and expertise. The threat of model theft — through extraction, distillation, or outright weight exfiltration — is real and increasingly operationalised. Here is the threat landscape and the realistic protections.
Add a small, carefully chosen perturbation to an image and a state-of-the-art classifier sees a school bus instead of a panda. Adversarial examples are the longest-running unresolved problem in machine-learning security and increasingly relevant to deployed systems.
An AIBOM lists everything that went into producing an AI model — base model, training data, fine-tuning corpora, dependencies, evaluation results. The concept is borrowed from software supply-chain security and increasingly required by regulators. Here is what an AIBOM actually contains and why it matters.