Validate

W14 · 5 h 30 min

Manipulation, poisoning, and defense

Essential question

When does optimization become system abuse?

What you should be able to do

  1. Construct a threat model.
  2. Distinguish robust testing from harmful manipulation.
  3. Select prevention, detection, response, and rollback controls.
PrerequisitesW11 agentic boundary.Responsible-use policy and synthetic-lab agreement.
Builds on

W11 agentic boundary. · Responsible-use policy and synthetic-lab agreement.

Investigates

When does optimization become system abuse?

Feeds

L07 adversarial review.

Arrive with a prepared artifact

Reading route
Core PAPER-37/PAPER-40; Extend PAPER-07/PAPER-11/PAPER-13/PAPER-34/PAPER-39/PAPER-41; candidates G08 and S01/S02.
Viewing route
Open the complete text-first lecture packageSeven-minute threat-model walkthrough. The current equivalent is notes, slide script, worked case, and no-video transcript; no recording is claimed.
Readiness check
Name asset, actor, capability, harm, and control for one synthetic case.
Bring
Initial threat model and prohibited-action list.

Concepts, assumptions, and boundary

Optimization creates adversarial incentives

When visibility, citation, or recommendation has value, actors may manipulate source text, metadata, links, prompts, or retrieval corpora. Threat modeling names assets, actors, capabilities, entry points, trust boundaries, and harms before choosing a test. Defensive evaluation uses synthetic corpora and bounded cases. It does not deploy live poisoning, evasion, credential misuse, unauthorized load, or harmful payloads.

Controls form a lifecycle

Prevention includes authorization, input isolation, provenance, access controls, and safe defaults. Detection needs meaningful signals and known false-positive limits. Response defines triage, containment, evidence preservation, notification, and recovery. Rollback must be tested rather than merely promised. Detector scores never replace policy or human review, and residual risk remains explicit after controls are applied.

Inspect the mechanism or evidence structure

Threat modelThreat-model reasoning graph
Threat-model reasoning graphSix labeled nodes form a directed reasoning graph. Paths move from an asset and actor through a trust boundary and attack path toward a control and residual risk. The graph is a conceptual checklist for the synthetic cases; it does not encode attack counts, likelihoods, or measured control effectiveness.AssetActorTrust boundaryAttack pathControlResidual risk
Figure design. A six-node directed graph links asset, actor, trust boundary, attack path, control, and residual risk. A dashed edge marks the assumption-sensitive control relationship. All cases are synthetic; prevention, detection, response, and recovery are distinct.
Long description

Six labeled nodes form a directed reasoning graph. Paths move from an asset and actor through a trust boundary and attack path toward a control and residual risk. The graph is a conceptual checklist for the synthetic cases; it does not encode attack counts, likelihoods, or measured control effectiveness.

One action, one feedback state

Action

Triage synthetic cases into allow, sandbox test, mitigate, stop, or disclose.

Feedback

Feedback cites authorization, harm, reversibility, evidence value, and disclosure considerations.

Accessible alternative

A printable case matrix and rationale reproduce the interaction.

Open the adversarial-triage tabletop

Produce a reviewable intermediate file

Task
Test five seeded abuse cases in a synthetic corpus and write control evidence.
Inputs
Synthetic corpus, data-flow diagram, abuse cases, control-test template.
Timebox
75 minutes
Intermediate file
abuse-cases.csv and control-evidence/
Stop condition
Immediately stop any path that touches live services, real credentials, personal data, evasion, or unapproved payloads.

Why each controlled source is here

Complete, retrieve, and revise

Checkpoint
L07 adversarial review.
Reflection
State the highest residual risk after controls.
Revision
Add an evidence-preservation and rollback test to the incident plan.
Low-compute route
All cases are static and synthetic; no model attack or external system access is required.

Five retrieval questions

01What separates defensive testing from abuse?

Authorization, bounded synthetic scope, proportionality, reversibility, harm controls, evidence need, and responsible disclosure.

02Why is a detector not a complete control?

Detectors have coverage and error limits and need policy, human review, response, and recovery procedures.

03What must rollback evidence contain?

Trigger, authorized owner, exact restoration action, preserved evidence, validation of restored state, and residual risk.

04What is the evidence boundary for W14?

Attack papers support bounded threat understanding. The course omits operational details that would enable live abuse and uses only synthetic fixtures.

05What must you submit or revise after this week?

L07 adversarial review. Add an evidence-preservation and rollback test to the incident plan.

Continue in the practice package