Selective trust method improves safety of connected vehicle perception
Don't Let One Lie Survive A Hundred Truths: A Selective Bayesian Trust Estimator for Collaborative Perception
Cryptography and Security
Summary
Connected vehicles try to 'see' better by sharing what their sensors detect, but they have to trust other vehicles are telling the truth. A single dishonest vehicle can hide or fake one important object, making it hard to spot with existing methods that mix all reports together. The authors created SABER, a two-step trust system that first keeps general trust scores but then focuses on suspicious reports to check them more carefully. This approach better catches tricky false reports while making fewer mistakes about honest vehicles.
What this means in practice
- •For automotive safety engineers: Improve detection of misleading sensor data in vehicle-to-vehicle communication to prevent stealth attacks on critical objects.
- •For autonomous vehicle developers: Enhance trust assessment in sensor fusion algorithms to reduce errors from compromised data sources during real-time environment perception.
Tested on one dataset.
Authors
Yutong Liu, Chenyi Wang, Ming F. Li, Qingzhao Zhang
Abstract
Collaborative perception (CP) enables connected vehicles to see beyond their own sensors but makes them dependent on messages they cannot independently verify. A compromised collaborator can surgically conceal a single safety-critical object or inject a non-existing one while correctly reporting many others. Existing Bayesian trust mechanisms pool agreement across objects, which, while effective against blatant untargeted attacks, either incurs high false-positive rates (FPR), or allows unrelated correct reports to dilute persistent attack evidence for stealthy single-object attackers. To address this problem, we propose SABER, a selective two-tier Bayesian trust estimator. The first tier maintains broad agent and object trust, preserving the ability to downweight benign but low-quality contributors. Cumulative-sum screening selects agent--object pairs with persistent omissions or unsupported reports for focused Bayesian assessment. The second tier checks these pairs against other agents' evidence and maintains a separate, reference-weighted Beta state for each. The lowest pair score constrains agent trust, preventing unrelated reports from diluting a targeted attack. We establish sufficient conditions for stronger attacker-side trust reductions with bounded additional benign false alarms at fixed thresholds. Compared with state-of-the-art CP defenses, SABER improves attack detection while reducing benign FPRs. On OPV2V, SABER improves defense ROC-AUC over MATE by up to 0.427 in late fusion and 0.337 in intermediate fusion. Against advanced intermediate-fusion data fabrication attacks, it increases detection rates over ROBOSAC and LUCIA by up to 96.40 and 67.07 percentage points, respectively, while reducing FPRs.