Game Theoretic Approaches for Deception and Counterdeception

Assistant Professor Zachary Sunberg

University of Colorado Boulder

May 5th, 2026

Why Game Theory?

Example context: air defense against maneuvering attackers.
Traditional approach: assume a model for the attacker, use optimal control to intercept.
Attacker can exploit this approach by behaving unpredictably (a form of deception).
If, instead, we play a Nash equilibrium strategy for a zero-sum game, the strategy is robust in the sense that we will do no worse if the other player changes their strategy.

Why Game Theory?

Is a Nash equilibrium strategy a good choice in real life against humans?

Yes! Example: Superhuman play in poker with deception through bluffing.

Part 1: Online Planning in POSGs

Tyler Becker

Joined DECODE AI project Fall 2024

Partially Observable Stochastic Games (POSGs)

Environment has state \(s \in S\)
Agents act simultaneously with \(a^i\) forming joint action \(\mathbf{a}\)
State transitions according to \(T(s' \mid s, \mathbf{a})\)
Each agent receives reward \(R^i(s, \mathbf{a}, s')\)
Each agent receives an observation \(o^i\) with distribution \(Z(o^i \mid \mathbf{a}, s')\)

State space \(S\)

Actions

\(\mathbf{a}\)

\(a^1\)

\(a^2\)

\(a^n\)

Environment with

shared state \(s\)

Policy \(\pi^1\)

Policy \(\pi^n\)

\(\vdots\)

Observations

\(\mathbf{o}\)

\(o^1\)

\(o^2\)

\(o^n\)

\(S = \mathbb{R}^{12}\)

\(\times \mathbb{R}^{12}\)

\(\times \mathbb{R}^{\infty}\)

POSGs: Challenges and Existing Tools

Large state spaces
Partial observations
Strategic opponents
Deception and counter-deception

Our approach: Build on these three tools

Tool	Good At	Missing
POMDP* solvers	State uncertainty	Strategic opponents
EFG** Solvers	Strategic opponents	Probabilistic beliefs
AlphaZero	Learned search	Simultaneous moves

* A POMDP (Partially Observable Markov Decision Process) is a single agent POSG (much easier)

** EFG = Extensive Form Game

Image: Russel & Norvig, AI, a modern approach

CDIT (conditional distribution infoset trees) = particles + information sets
Particles approximate hidden state
Information sets preserve strategic uncertainty
CFR (counterfactual regret minimization) searches for low-exploitability policies

Particle-Filter POSGs

Test Environment: Partially Observable Tag

[Becker & Sunberg, AAMAS 2025]

Equilibrium policies are stochastic and hide intent
Exploitability measures vulnerability - demonstrably decreases

What the CDIT Gives Us

[Becker & Sunberg, AAMAS 2025]

Equilibrium search without state enumeration
Continuous-state POSG planning
Probabilistic exploitability bounds
No direct dependence on state space size

Combining with Learning: Simultaneous Alpha Zero

AlphaZero assumes turn-taking
Markov Games (e.g. POSGs) move simultaneously
Each state becomes a matrix game
Search improves both players' policies

Alpha Zero

SimultaneousAlpha Zero

(Ours)

Search Improves Robustness

Best-response value improves; exploitability falls
Mixed actions prevent exploitation
Deeper search provably reduces exploitability

Counter-Deception in SDA

Target exploits eclipse and occlusion
Observer learns sensing geometry and robust manuevering strategies

Observer satellite seeks well-illuminated vantage-points of target satellite

Part 2: Optimal Deception on Shared Channels

Mel Krusniak

Joined DECODE AI project Jan. 2026

Motivation: Informed Pursuit-Evasion

Past work: How do we teach adversarial agents in trajectory space to hide and seek information about each other?

Present work: How do we teach a higher-level broadcaster to publicly share the "right" information with an ally?

Goal: Optimal Informer
Behavior

Consider a three player interaction with one player at a higher informational level.

Pursuer, Evader: Competition with side goals, acting based on semi-public information.
Informer: Sees the full state. Determines what semi-public information is broadcast.

Research thrust: Automatically choose what information to broadcast, what channel to use, and how precisely to convey it.

Preliminary Methods

"When should I lie?"
(or "what channels are safe?")

Test environment: Discrete tag in a 2x2 grid.
Four states, two bits of information.

"When should I lie?"
(or "what channels are safe?")

Test environment: Discrete tag in a 2x2 grid.
Four states, two bits of information.

Adversariality: Evader has a side goal.
It seeks a goal state with weight (1-⍴).
Goal is random, but seen by the informer.
Noise: Pursuer has worse observations.
The second bit (or "channel") is perturbed with probability ⍵.

\[r^{(\text{evd})}(a) = (1 - \rho) \; r^{(\text{evd})}_{\text{reach\_goal}}(a) + \rho \;r^{(\text{evd})}_{\text{avoid\_psr}}(a)\]

Long Term Goals

This is one example of an "information game." Others of interest include:

Channel takeover prevention / "confirm-then-commit" tactics
Dogwhistle / "double speak" identification
Information denial via mixed strategies

Game theory, machine learning, and control theory all contribute useful tools, but converting between formalizations is fraught, error-prone, and inefficient.