arXiv subjects

Caterina Cinel

Publications and source records attributed to Caterina Cinel.

3 recordsLinked to original sources

arXiv2026

The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams

The speed and accuracy of an artificial teammate fundamentally alter the failure states of Human-AI integration. While high-speed AI interventions risk inducing reflexive blind compliance, delayed interventions can induce ambiguous cognitive conflict. This study investigates how the fundamental characteristics of an in-task AI assistant, Fast/Less-Accurate (FLA-AI) versus Slow/Accurate (SA-AI) impact the synergy of Collaborative Brain-Computer Interface (cBCI) teams in a Virtual Reality drone task. Seventeen operators completed continuous search tasks under high cognitive workload while their spatial covariance was mapped using a 2D Adaptive Riemannian Oracle. The results mathematically demonstrate that AI timing dictates the mechanism of team failure. Fast AI induced instant, blind compliance; human accuracy under deception collapsed to 50.2%, and pure behavioural teams (N=8) failed to scale beyond 74.1%. In contrast, Slow AI induced delayed cognitive conflict; humans hesitated (61.1% accuracy), but N=8 behavioural teams eventually recovered to 100.0%. Crucially, the Riemannian Oracle mathematically adapted to these states: it heavily restricted temporal windows (< 0.8s) to intercept fast reflexive compliance, while widening windows (> 1.2s) to capture delayed cognitive conflict. Integrating these isolated veridical signals via Hybrid Fusion successfully rescued the Fast AI team (+7.6% at N=8) and significantly accelerated the recovery of smaller Slow AI teams (+6.9% at N=4). These findings prove that cBCI synergy is heavily contingent on the temporal dynamics of trust, providing a critical framework for designing dynamically gated Human-AI systems.

cs.HC↗

arXiv2025

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

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. Using a passive BCI (pBCI) framework validated via offline simulation, we compared 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 42.6% (worse than chance). The NDT, however, maintained a robust 68.3% accuracy. While this did not exceed the best individual's theoretical maximum, it provided a critical +25.7% "Safety Net Delta" that prevented the team from succumbing to the correlated error. This resilience was explained by a neuro-behavioural decoupling, where the BCI's predictions relied on preserved posterior-visual processing ("The Truth Signal") while the operators' executive monitoring systems collapsed. We conclude that an implicit BCI provides resilience by learning to bypass a compromised executive networks and access the preserved sensory representation of ground truth, defending against AI-induced error in high-stakes environments.

cs.HC↗

arXiv2025

Quantifying Emotional Arousal through Pupillary Response: A Novel Approach for Isolating the Luminosity Effect and Predicting Affective States

Pupil dilation is recognized as an objective indicator of emotional arousal, but confounding factors such as the luminosity of stimuli and the surrounding environment have greatly limited its practical usefulness. This study presents a new approach to isolate and remove the effect of luminosity on pupil dilation. We validated this approach by showing 32 video clips with different content and emotional intensity to 47 participants, who reported their level of emotional arousal after each video. We developed a model capable of predicting the effect of luminosity on pupil size as a function of screen brightness, which adapts to individual physiological differences and different types of monitors through a brief pre-experimental calibration. We thus estimated the pupil size due exclusively to luminosity and subtracted it from the total recorded pupil size, obtaining the component due exclusively to arousal. From the latter, we predicted the arousal of each participant for each video using two models. We first used a simple linear regression model. When we used the luminosity-corrected pupil size, we obtained a correlation between predicted and self-reported arousal of r = 0.65 +/- 0.12, and R2 of 0.43 +/- 0.12. The uncorrected pupil size, instead, showed virtually no predictive power (r = 0.26 +/- 0.15, R2 = 0.09 +/- 0.089). We then used an Extreme Gradient Boosting model, obtaining even better results in the case of luminosity correction (r = 0.765 +/- 0.047, R2 = 0.556 +/- 0.085). Our results highlight that separating emotional and luminosity components from pupillary responses is crucial for accurately predicting arousal.

cs.HC↗