🤖 AI Summary
Existing continuous observation models fail in sparse binary rating networks—such as Bitcoin-OTC—due to data discretization, hindering effective trust fraud detection. This work proposes the first sequential detection framework tailored for such networks, combining an accurate parametric model derived from empirical distributions with a dual-mechanism architecture that integrates Bernoulli CUSUM and asymmetric rating modulation to jointly capture behavioral shifts and rating dynamics. Theoretically, we derive a Bayesian-optimal F1 upper bound based on empirical parameters and demonstrate that detector–model alignment outweighs raw information quantity in detection efficacy. Experiments on Bitcoin-OTC and Bitcoin-Alpha achieve AUC scores of 0.749 and 0.796, respectively, significantly outperforming GaaSTrust (p < 0.003), with founder-labeled instances attaining an AUC of 0.999.
📝 Abstract
Sequential trust detection in rating networks relies on continuous observation models that fail on real data. On Bitcoin-OTC, 56\% of ratings take a single value under standard mapping, breaking the distributional assumptions that parametric detectors require. This paper makes three contributions. It derives a Bayes-optimal F1 detection ceiling for per-node sequential detectors using empirically measured observation parameters. At Bitcoin-OTC's median in-degree of 2, this ceiling falls to 0.451 for strategic attacks, explaining why unsupervised methods cluster near $F1 \approx 0.4$. The analysis shows that detector-model matching, not information content, determines performance: binary models retain 86\% of mutual information while enabling exact parametric fit. A dual-regime architecture is presented where Bernoulli CUSUM detects behavioral shifts and triggers asymmetric scoring. Ablation reveals a co-design constraint: the modulation mechanism improves AUC by 0.030 on binary observations but degrades it by 0.094 on continuous observations. The combined system achieves AUC 0.749 on Bitcoin-OTC and 0.796 on Bitcoin-Alpha, beating GaaSTrust on all 8 attacks ($p < 0.003$), with founder-label AUC of 0.999.