teleo-codex/domains/ai-alignment/representation-trajectory-geometry-distinguishes-deceptive-from-sincere-alignment-without-creating-adversarial-attack-surfaces.md

## The Claim (current version)
**Source:** Theseus synthetic analysis of multi-layer SCAV feasibility
Multi-layer trajectory geometry monitoring (ensemble probes across layers) *is predicted to* create adversarial attack surface in white-box settings. White-box multi-layer SCAV *is theoretically capable of suppressing* concept directions at all monitored layers simultaneously. The claim that trajectory geometry avoids attack surfaces may need qualification: it may hold only for black-box adversaries if rotation patterns are model-specific, but not for white-box adversaries with access to model weights.