Controlled ambiguity as an experimental defence against AI reconnaissance.
UNMODELLED research · Project Rorschach · The Mask
Fig. 1 — Three disciplines, four overlaps. Conceptual illustration, not results: the centre combines bounded observation-layer perturbations, deception and measurement as a hypothesis. Tap a region.
04 · Rorschach investigation
Proposed investigation: combine bounded observation-layer perturbations, decoy exposure and measurement. Test reconstruction accuracy and reconnaissance cost; effectiveness is untested.
What can an agent learn, and what does it cost?
The hypothesis is that bounded observation-layer perturbations may reduce an autonomous cyber agent’s reconstruction accuracy or increase reconnaissance cost. Behavioural telemetry records observable actions, not model-generated reasoning. Agents may be legitimate; risk signals alone do not establish identity or malicious intent.
The Intent Gap addresses the complementary action-side problem: how to independently constrain consequential operations when an authenticated agent's objectives cannot reliably be inferred. Rorschach instead investigates the accuracy and cost of the information an adversarial agent acquires.
The four overlapsRelated approaches and evaluation questions
01Bot × Moving target
Challenges that move.
Changing automated-client challenges can vary the observations a client receives. Their responses are behavioural signals, not proof of automation, malicious intent or a particular reasoning engine.
What friction reaches legitimate users and agents?
How do results vary across tools and environments?
02Bot × Deception
Detect, then divert.
Combine risk signals with controlled decoy routing for suspected adversarial activity. Automation alone is not a routing justification: legitimate agents need protection within predefined impact limits.
Research context
Context: Risk signals + decoys
What to measure
Decoy interactions and reconstruction accuracy
False positives and legitimate-client impact
Observable actions within bounded exposure
03Moving target × Deception
Traps that shift.
Changing exposure plus decoys draws on moving-target defence and deception. Selected observations may vary without requiring changes to real underlying state or access policy; effects must be tested in the chosen environment.
Related approaches
Context: MTD + deception
Evaluation questions
Does changing exposure alter reconstruction?
What cost does a client incur versus baselines?
Does benefit persist when the mechanism is known?
04All three · Rorschach
A proposed investigation.
The Mask is the experimental control in Project Rorschach, UNMODELLED’s public research programme. The proposed contribution is bounded observation-layer perturbations and adaptive feedback compared with baselines. Drift Identity and Entropy Engine are experimental mechanisms/applications in this scope.
Research context
Programme: Project RorschachControl: The Mask
Supporting behavioural measures
Response latency under controlled variation
Choice sequences through available paths
Retries and looping behaviour
Tool and command selection — not reasoning-engine identification
The Convergence Map is a proposed framework connecting authority, adaptive defence and operational resilience. It supports evaluation questions; it is not evidence that the combined system has been implemented or validated.
Hypothesis and uncertaintyEffects depend on the agent and environment.
Reconstruction accuracy
A less accurate map?
Compare reconstructed facts with known ground truth under selected observation changes. Humans and models do not all respond alike; classification is a secondary exploratory question.
Reconnaissance cost
More effort to learn?
Measure requests, elapsed time and resource use against baselines. Effects may depend on tools, tasks and prior knowledge. No perception benchmark establishes security effectiveness here.
UNTESTED
Effectiveness must be measured in the target environment.
Who must be evaluatedEvaluation concerns, not measured rankings
Scripted clientsParsing, retries and task completionTo evaluate
Browser automationNavigation and completion under changing viewsTo evaluate
Autonomous agentsReconstruction accuracy and reconnaissance costTo evaluate
AI web scraperExtraction accuracy and authorised useTo evaluate
AI-assisted humanHuman correction, workload and task successTo evaluate
Legitimate humanUsability, trust and completion within limitsImpact limits
Assistive technologyNavigation and comprehension within impact limitsImpact limits
Machine-readable content can reach humans and screen readers. Legitimate clients and accessibility tools must remain within predefined impact limits; zero impact has not been established.
Questions to test
Reconstruction accuracyprimary
Reconnaissance costprimary
Human / agent classificationexploratory
Exact-model attributionexploratory
Legitimate-client impactbounded
Does benefit persist against an adversary who knows the mechanism? That is a test question, not a guarantee of resource exhaustion.
Set thresholds before testing for practically meaningful effects on reconstruction accuracy or reconnaissance cost and predefined legitimate-impact limits. Match change budgets and decoy exposure across comparisons. Path divergence alone is not attack prevention.
Research decision
Proceed to bounded evaluation.
Security Sages publishes this concept-stage brief. UNMODELLED is the overarching research project; Project Rorschach is a public research programme, not an internal codename. There are no published UNMODELLED experimental results. Human Checkpoints and Assurance Integrity are separate research outside Rorschach and The Mask.
Descriptive research terminologySemantic MTD · not a validated protocol