Search papers, labs, and topics across Lattice.
This paper addresses the issue of behavioral privacy leakage in autonomous negotiation agents, which can lead to the inference of private constraints by adversaries. By developing an adaptive stochastic negotiation policy that ensures $(\varepsilon, \delta)$-differential privacy while maintaining high negotiation utility and almost-sure convergence, the authors provide a robust solution to this subtle threat. The proposed mechanism significantly reduces adversarial inference accuracy by 43-50% across 3,000 synthetic bilateral negotiations, demonstrating that effective privacy measures can coexist with performance efficiency.
Behavioral privacy leakage can be mitigated without sacrificing negotiation success or utility, achieving a 43-50% reduction in adversarial inference accuracy.
Autonomous negotiation agents are increasingly deployed in high-stakes settings such as insurance and procurement. While cryptographic techniques protect explicitly disclosed constraint values, they fail to address a subtler threat: behavioral privacy leakage, where an adversary infers private constraints from observable negotiation dynamics such as concession trajectories, timing, and convergence patterns. This paper investigates behavioral differential privacy in multi-round negotiation protocols. We design an adaptive stochastic negotiation policy that jointly guarantees $(\varepsilon, \delta)$-differential privacy, almost-sure convergence of the offer sequence (reaching agreement when the counterparty's reservation value permits), and high negotiation utility. Evaluated on 3,000 synthetic bilateral negotiations, our mechanism reduces adversarial inference accuracy by 43-50% while maintaining a negotiation success rate and utility above 90%, demonstrating that strong privacy guarantees can be achieved without significant loss of performance.
