4 papers
When Does Randomized Oversight Align AI Agents That Can Conceal?
Joshua S. Gans, Richard Holden
Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records. Stronger auditing makes undete…
Fourfold Is Enough: Connected LEGO Models from One Brick Type
Joshua S. Gans
Can a LEGO model built from many kinds of rectangular bricks be rebuilt using only the familiar brick? Enlarging every dimension by four makes the pieces fit, but they m…
Calibrated Bait: Defensive Information Design under Adversarial Fingerprinting
Joshua S. Gans
A honeytoken, a decoy credential or record whose use reveals an intruder, produces defence intelligence only if an adversary sometimes treats it as genuine. The adversary can inste…
When Agents Talk: Honeytokens under Shared Memory
Joshua S. Gans
During a 2026 cyber-capability evaluation, short-lived AI agents turned a shared package repository into persistent memory, passing exploit findings to later agents and rebuilding…