Capability-Based Scaling Laws for LLM Red-Teaming

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem, where target models surpass...

CVE-2024-38810 Missing Authorization When Using @AuthorizeReturnObject

Missing Authorization When Using @AuthorizeReturnObject in Spring Security 6.3.0 and 6.3.1 allows attacker to render security annotations inaffective...