Human-AI Teaming Under Deception: An Implicit BCI Safeguards Drone Team Performance in Virtual Reality

2025-11-24

AI Summary

Human-AI teams exhibit catastrophic decision failures under AI-delivered erroneous feedback and high cognitive load; conventional voting-based aggregation mechanisms are highly susceptible to contamination by misleading AI signals. Method: We propose a robust interference-resistant collaborative brain-computer interface (cBCI) framework that acquires pre-behavioral prefrontal neural confidence signals via EEG, establishing a neuro-behavioral decoupling mechanism for implicit, robust correction of AI deception. Results: In a VR-based drone surveillance task with adversarial AI misdirection, baseline voting accuracy plummeted to 44%, whereas our method achieved 98% accuracy (p < .001), significantly surpassing the best individual human performance. The core contribution is the first demonstration of leveraging preconscious neural confidence biomarkers—bypassing behavioral-level deception—to enable neuro-grounded, trustworthy group decision aggregation. This establishes a novel paradigm for high-stakes human-AI collaboration.

Technology Category

• Humans and AI: Voting
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Human-AI teams can be vulnerable to catastrophic failure when feedback from the AI is incorrect, especially under high cognitive workload. Traditional team aggregation methods, such as voting, are susceptible to these AI errors, which can actively bias the behaviour of each individual and inflate the likelihood of an erroneous group decision. We hypothesised that a collaborative Brain-Computer Interface (cBCI) using neural activity collected before a behavioural decision is made can provide a source of information that is decoupled from this biased behaviour, thereby protecting the team from the deleterious influence of AI error. We tested this in a VR drone surveillance task where teams of operators faced high workload and systematically misleading AI cues, comparing traditional behaviour-based team strategies against a purely Neuro-Decoupled Team (NDT) that used only BCI confidence scores derived from pre-response EEG. Under AI deception, behaviour-based teams catastrophically failed, with Majority Vote accuracy collapsing to 44%. The NDT, however, maintained 98% accuracy, a statistically significant synergistic gain over even the team's best individual performer (p < .001). This was explained by a neuro-behavioural decoupling, where the BCI's predictions remained highly accurate while the operator's subjective confidence became an unreliable signal. We conclude that an implicit BCI provides resilience by learning to adapt its neural strategy, shifting from relying on signals of efficient, autopilot processing in simple conditions to interpreting signatures of effortful deliberation when confronted with cognitive conflict. This demonstrates a system that leverages the context of the neural signal to defend against AI-induced error in high-stakes environments.

Problem

• Protecting human-AI teams from catastrophic failure caused by deceptive AI feedback
• Using brain-computer interfaces to decouple neural signals from biased behavior
• Maintaining team performance under high cognitive workload and AI deception

Innovation

• Implicit BCI safeguards drone teams from AI deception
• Neuro-decoupled teams use pre-response EEG confidence scores
• BCI adapts neural strategy to maintain accuracy under conflict