面向网络侦察欺骗的差分隐私指纹混淆机制

Differential Privacy Based Fingerprinting Obfuscation Mechanism Towards Network Reconnaissance Deception

网络指纹探测作为一种重要的网络侦察手段,可以被攻击者用于获取目标网络的指纹特征,进而为后续开展有针对性的攻击行动提供支持。指纹混淆技术通过主动修改响应分组中的指纹特征,能够让攻击者形成虚假的指纹视图,但现有的混淆方法在应对攻击者策略性探测分析方面仍存在不足。为此,提出了一种面向网络侦察欺骗的差分隐私指纹混淆机制(Differential Privacy based Obfuscation of Fingerprinting,DPOF)。DPOF参考数据隐私保护的思想,首先建立了效用驱动的差分隐私指纹混淆模型,通过差分隐私指数机制计算不同效用虚假指纹的混淆概率,在此基础上进一步设计了资源约束下的指纹混淆决策方法,并实现了基于粒子群优化的混淆策略求解算法。仿真实验结果表明,相比现有的典型指纹混淆方法,DPOF在不同问题规模和预算情况下均具有更优的指纹混淆效果,且能够以更快的速度获得更好的近似最优策略。

Network fingerprinting detection is an important network reconnaissance method,which can be used by attackers to obtain the fingerprinting characteristics of the target network,and then provide support for subsequent targeted attacks.Fingerprinting obfuscation technology enables attackers to form fake fingerprinting views by actively modifying the fingerprinting features in response packets.However,existing obfuscation methods are still insufficient in dealing with attackers’strategic detection and analysis.To this end,a differential privacy based fingerprinting obfuscation mechanism(DPOF)towards network reconnaissance deception is proposed.Taking the idea of data privacy protection as a reference,DPOF first establishes a utility-driven differential privacy fingerprinting obfuscation model,and calculates the obfuscation probability of fake fingerprints with different utilities through the differential privacy exponential mechanism.On this basis,a fingerprinting obfuscation decision method under resource constraint is further designed,and an obfuscation strategy solving algorithm based on particle swarm optimization is implemented.Simulation results show that compared with the existing typical fingerprinting obfuscation methods,DPOF has better fingerprinting obfuscation effect with different problem scales and budgets,and can obtain a better approximate optimal strategy at a faster speed.