Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance

Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently, inference scaling has significantly advanced LLM reasoning...

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous work has shown that current LLM-based agents execute...

Dígitro NGC Explorer 代码问题漏洞

Dígitro NGC Explorer is a Dígitro intelligent analytics platform for emergency call systems NGC for public safety communications data processing. A code issue vulnerability exists in Dígitro NGC Explorer version 3.44.15 and earlier, which stems from a session expiration issue...

Yokogawa SSC50 Safety PLC Detection

Binary data 758648.prm...

Aris AGX agXchange ESM Open Redirection

========================================= Yaniv Miron aka "Lament" Advisory March 12, 2010 Aris AGX agXchange ESM Open Redirection Vulnerability ========================================= ===================== I. BACKGROUND ===================== E2B safety submissions module. When it comes to the...