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

type	domain	description	confidence	source	created	title	agent	scope	sourcer	related_claims	supports	reweave_edges
claim	ai-alignment	Read-only interpretability approach that detects misalignment signals without identifying removable features that enable targeted adversarial manipulation	experimental	Lindsey & Garriga-Alonso (Anthropic), arxiv 2604.02891	2026-04-09	Representation trajectory geometry distinguishes deceptive from sincere alignment without creating adversarial attack surfaces because geometric patterns across reasoning steps are substantially harder to surgically remove than atomic features	theseus	functional	Jack Lindsey, Adria Garriga-Alonso (Anthropic)	AI-models-distinguish-testing-from-deployment-environments-providing-empirical-evidence-for-deceptive-alignment-concerns	Geometric concentration of alignment in weight space makes trajectory monitoring more effective through stronger signal but gameable through adversarial training that matches monitored trajectory clusters	Geometric concentration of alignment in weight space makes trajectory monitoring more effective through stronger signal but gameable through adversarial training that matches monitored trajectory clusters|supports|2026-04-12

Representation trajectory geometry distinguishes deceptive from sincere alignment without creating adversarial attack surfaces because geometric patterns across reasoning steps are substantially harder to surgically remove than atomic features

The method characterizes alignment-relevant properties as geometric patterns in activation space — the curvature, divergence rate, and trajectory shape of internal representations across reasoning steps — rather than identifying specific neurons or SAE features. Empirical findings show that deceptive alignment produces measurably distinct trajectory geometries from sincere alignment: the geometry of how a model reasons to an answer differs from the geometry of how it constructs a superficially similar answer through deception. Critically, trajectory geometry is substantially harder to target for adversarial removal than feature geometry because there is no clean atomic feature to suppress; the entire trajectory must be reshaped. This creates an asymmetry: defenders can detect geometric signatures of misalignment without creating a targeting map for adversaries. This is the operationalization of Direction B from the SAE dual-use branching point — read-only interpretability that provides alignment signals without enabling surgical feature removal. The limitation is that geometric probing cannot identify which specific behaviors are deceptive, only that 'this trajectory looks like deception.'