ID	原文	译文
3853	在该机制中，将最大化域间互操作性和最小化域内自治性作为目标函数，将 7 类典型的跨域冲突作为约束函数，设计了一种带约束的 NSGA-III 优化算法。	Both the maximization of inter-domain interoperabil-ity and the minimization of intra-domain autonomy were taken as the objectives. Further, seven constraints were designedto prevent typical cross-domain conflicts. To solve the optimization problem, a constrained NSGA-III algorithm wasproposed.
3854	实验结果表明，在模拟现实机构特征的大中规模数据集上，该算法拥有较快收敛速度，且解集具有较高的准确性。	The experimental results show that the proposed algorithm can quickly converge and accurately find the policy mapping even in the large-scale datasets.
3855	为解决分子通信中由分子扩散带来的码间干扰（ISI）和背景噪声这 2 个严峻的挑战，采用 4 种能抵抗 ISI的信号特征表示接收信号的瞬态特性，提出了可靠的不依赖于信道冲激响应（CIR）的非相干分子信号检测算法，并设计了自适应阈值计算方法，且给出了误比特率（BER）理论值。	To solve the inter-symbol interference (ISI) and background noise challenges of molecular communication viadiffusion (MCvD), four ISI-resistant signal-features were deployed, and a reliable non-coherent signal detection algo-rithm, which was insensitive to different types of molecular channel impulse response (CIR), was proposed. Also, anadaptive decision threshold and theoretical bound of bit error rate (BER) were deduced.
3856	仿真结果显示，在同等计算复杂度下所提方案 BER 比传统方案 BER 低，因此在计算能力受限的纳米级分子通信系统中具有广泛的应用前景。	Simulation results demonstrate alower BER of the proposed non-coherent scheme compared to the state-of-the-art schemes in the same order of computa-tional complexity, therefore suggesting its potential applications for future nano-scale MC.
3857	为了应对流量分类攻击，从防御者的角度出发，提出了一种基于对抗样本的网络欺骗流量生成方法。	In order to prevent attacker traffic classification attacks, a method for generating deception traffic based onadversarial samples from the perspective of the defender was proposed.
3858	通过在正常的网络流量中增加扰动，形成欺骗流量的对抗样本，使攻击者在实施以深度学习模型为基础的流量分类攻击时出现分类错误，欺骗攻击者从而导致攻击失败，并造成攻击者时间和精力的消耗。	By adding perturbation to the normal networktraffic, an adversarial sample of deception traffic was formed, so that an attacker could make a misclassification whenimplementing a traffic analysis attack based on a deep learning model, achieving deception effect by causing the attackerto consume time and energy.
3859	采用几种不同的扰动生成方法形成网络流量对抗样本，选择 LeNet-5 深度卷积神经网络作为攻击者使用的流量分类模型实施欺骗，通过实验验证了所提方法的有效性，为流量混淆和欺骗提供了新的方法。	Several different methods for crafting perturbation were used to generate adversarial sam-ples of deception traffic, and the LeNet-5 deep convolutional neural network was selected as a traffic classification modelfor attackers to deceive. The effectiveness of the proposed method is verified by experiments, which provides a new method for network traffic obfuscation and deception.
3860	为了在混合型传输网络中为用户提供更加灵活而便利的服务，提出了一种采用单个光调制器同时提供有线和单边带无线服务的系统。	In order to provide more flexible and convenient service for users in the hybrid transmission network, anovel system using a single optical modulator to provide wired and single side band (SSB) wireless signal was pro-posed.
3861	通过结合双极化二进制相移键控调制器、相位调节器等器件的应用，直接产生有线和单边带无线信号，抑制色散引起的走离效应，并成功实现10 Gbit/s有线信号和承载于40 GHz毫米波上的5 Gbit/s单边带无线信号在 65 km 单模光纤中的有效传输。	By combining the application of dual-polarization binary phase shift keying modulator (DP-BPSK), phaseshifter and other devices, wired and SSB wireless signals were directly generated to suppress the walk-off effectcaused by dispersion, and the effective transmission of 5 Gbit/s SSB wireless signal carried on 40 GHz millimeterwave and 10 Gbit/s wired signal over 65 km single-mode fiber (SMF) were successfully achieved.
3862	实验结果表明，偏振复用技术和光副载波复用等技术的应用使信号在传输速率和性能上有了更大的提升，并将在未来宽带通信网中发挥重要作用。	The experiments show that the application of polarization multiplexing technology and optical subcarrier multiplexing technology canmake the signal have a greater improvement in transmission rate and performance, and play an important role in thefuture broadband communication network.