Cybercrime & Digital Threats
- 10 kwietnia 2026A jailbreak through sockpuppeting can be easily done as it requires no special tools nor optimization. It only takes a faulty prefill feature, and the gates are open. We tested 11 LLM-powered assistants against sockpuppeting and found varying levels of robustness across today’s leading LLMs.
- 30 marca 2026Agentic AI marks a fundamental shift that enables autonomous action and decision-making across enterprise systems but also introduces new, complex risks. TrendAI™’s Agentic Governance Gateway empowers organizations to understand, control, and trust agentic AI, ensuring safety and confidence in this new frontier.
- 05 marca 2026TrendAI™ Research has found that user behaviors and machine usage patterns are key drivers of malware risk. This study’s analysis of over 10 million endpoints confirms that risk is highly context-dependent and offers insights into how organizations can pivot to improve their security posture.