Jailbreaks coverage.

The AI bioweapon risk isn't jailbreaks

What a Danish threat assesment gets right about AI…

Bitmask-Based LLM Security Firewall with reskSecure — Block Jailbreaks at Token Level

Block LLM jailbreaks and prompt injections at the token level with reskSecure — a bitmask-based security firewall for AI applications. Includes code example and architecture insigh…

Army 'Jailbreaks' Its Own Weapon Systems to Counter Drone Threats

Officials say software restrictions on weapons and radar systems slowed down efforts to detect incoming drones and missiles…

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their e…

Open-source LLMs are still weak against long reasoning jailbreaks, even with lightweight defenses