Prompt Injection: An Analysis of Recent LLM Security Incidents
agosto 26, 2025
Overview With the widespread application of LLM technology, data leakage incidents caused by prompt word injections are increasing. Many emerging attack methods, such as inducing AI models to execute malicious instructions through prompt words, and even rendering sensitive information into pictures to evade traditional detection, are posing serious challenges to data security. At the same […]
A Deep Analysis of the Ransomware Group Babuk2’s Recent Activities
março 28, 2025
Overview Recently, NSFOCUS CERT detected that the Babuk2 group has been frequently publishing sensitive data of several well-known organizations on its dark web site. The data is from multiple sectors, including government, finance, internet, healthcare, and education, across various countries and regions. Up to this month, at least 71 victims’ data has been disclosed, and […]
