148 citations · 152 across the 5 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators
Dominik Schwarz
An activation-based safety gate must distinguish harmful assistance from legitimate work on the same topic. We test whether probes trained on broad harmful-versus-harmless data pro…
cs.CR2025★ 2 cited
Countermind: A Multi-Layered Security Architecture for Large Language Models
Dominik Schwarz
The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are…