[论文解读] Set-based Obfuscation for Strong PUFs against Machine Learning Attacks
本文提出随机集混淆(RSO),一种轻量级防御机制,用于抵御强物理不可克隆函数(PUF)的机器学习攻击。该机制利用预先存储的稳定PUF响应集合与真随机数生成器(TRNG),通过异或(XOR)操作对挑战-响应对进行混淆,以极低的硬件开销防止机器学习攻击。当攻击者收集的挑战-响应对(CRP)超过阈值时,响应集合将被动态更新,使多种先进机器学习模型的预测准确率始终维持在约50%——等同于随机猜测水平。
Strong physical unclonable function (PUF) is a promising solution for device authentication in resourceconstrained applications but vulnerable to machine learning attacks. In order to resist such attack, many defenses have been proposed in recent years. However, these defenses incur high hardware overhead, degenerate reliability and are inefficient against advanced machine learning attacks such as approximation attacks. In order to address these issues, we propose a Random Set-based Obfuscation (RSO) for Strong PUFs to resist machine learning attacks. The basic idea is that several stable responses are derived from the PUF itself and pre-stored as the set for obfuscation in the testing phase, and then a true random number generator is used to select any two keys to obfuscate challenges and responses with XOR operations. When the number of challenge-response pairs (CRPs) collected by the attacker exceeds the given threshold, the set will be updated immediately. In this way, machine learning attacks can be prevented with extremely low hardware overhead. Experimental results show that for a 64x64 Arbiter PUF, when the size of set is 32 and even if 1 million CRPs are collected by attackers, the prediction accuracies of Logistic regression, support vector machines, artificial neural network, convolutional neural network and covariance matrix adaptive evolutionary strategy are about 50% which is equivalent to the random guessing.
研究动机与目标
- 解决强PUF对机器学习攻击(尤其是近似攻击和CMA-ES攻击)的脆弱性问题。
- 克服以往防御方案存在的高硬件开销、可靠性下降或对先进机器学习技术失效的局限性。
- 设计一种通用、低开销且可靠的混淆机制,兼容所有强PUF类型。
- 实现响应集的动态更新,确保在持续收集CRP的情况下仍能维持安全性。
- 确保该方案可部署于资源受限的物联网(IoT)环境。
提出的方法
- 在初始化阶段,从PUF本身提取一组稳定响应,并预先存储为混淆密钥集。
- 使用真随机数生成器(TRNG)为每个挑战-响应对随机选择集合中的两个密钥。
- 通过异或(XOR)操作对挑战和响应进行混淆,使用所选的两个密钥。
- 设定CRP收集的阈值;当超过该阈值时,立即更新响应集以破坏攻击者的建模能力。
- 在测试阶段应用混淆机制,隐藏真实PUF映射关系,防止攻击者逆向推导。
- 确保混淆过程不会降低PUF的可靠性,因为与随机值进行XOR操作可保持响应稳定性。
实验结果
研究问题
- RQ1是否能够通过低开销的混淆技术有效抵御强PUF的先进机器学习攻击,同时不降低可靠性?
- RQ2响应集的大小如何影响混淆后PUF系统的安全性和误码率?
- RQ3动态响应集更新能否阻止攻击者收集足够多的CRP以训练出高精度模型?
- RQ4在实际认证场景中,RSO对错误接受率(FAR)和错误拒绝率(FRR)有何影响?
- RQ5与现有混淆技术(如Controlled-PUF、PUF-FSM和Slender PUF)相比,RSO的硬件开销如何?
主要发现
- 对于64×64的仲裁器PUF,当响应集大小为32时,即使收集了100万组CRP,所有测试机器学习模型(逻辑回归、SVM、ANN、CNN、CMA-ES)的预测准确率均降至约50%。
- 64×64 RSO增强型仲裁器PUF的等错误率(EER)为1.7×10⁻⁶,符合实际安全标准。
- 128×128 RSO增强型仲裁器PUF的EER为8.9×10⁻¹¹,表明其错误率极低,适用于高安全等级应用场景。
- RSO增强型PUF在FPGA上仅消耗405个LUT和181个DFF,显著低于Controlled-PUF(1830 LUT)、PUF-FSM(960 LUT)和Slender PUF(1168 LUT)。
- TRNG和混淆逻辑可复用于现有系统,或从亚稳态PUF响应中提取,从而最小化额外硬件开销。
- 该方法可广泛适用于所有强PUF类型,且因XOR混淆机制的特性,不会损害PUF的可靠性。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。