This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks. Semantic communications aims to convey a desired meaning while transferring information from a transmitter to its receiver. An encoder-decoder pair that is represented by two deep neural networks (DNNs) as part of an autoencoder is trained to reconstruct signals such as images at the receiver by transmitting latent features of small size over a limited number of channel uses. In the meantime, another DNN of a semantic task classifier at the receiver is jointly trained with the autoencoder to check the meaning conveyed to the receiver. The complex decision space of the DNNs makes semantic communications susceptible to adversarial manipulations. In a backdoor (Trojan) attack, the adversary adds triggers to a small portion of training samples and changes the label to a target label. When the transfer of images is considered, the triggers can be added to the images or equivalently to the corresponding transmitted or received signals. In test time, the adversary activates these triggers by providing poisoned samples as input to the encoder (or decoder) of semantic communications. The backdoor attack can effectively change the semantic information transferred for the poisoned input samples to a target meaning. As the performance of semantic communications improves with the signal-to-noise ratio and the number of channel uses, the success of the backdoor attack increases as well. Also, increasing the Trojan ratio in training data makes the attack more successful. In the meantime, the effect of this attack on the unpoisoned input samples remains limited. Overall, this paper shows that the backdoor attack poses a serious threat to semantic communications and presents novel design guidelines to preserve the meaning of transferred information in the presence of backdoor attacks.

Semantic communications seeks to transfer information from a source while conveying a desired meaning to its destination. We model the transmitter-receiver functionalities as an autoencoder followed by a task classifier that evaluates the meaning of the information conveyed to the receiver. The autoencoder consists of an encoder at the transmitter to jointly model source coding, channel coding, and modulation, and a decoder at the receiver to jointly model demodulation, channel decoding and source decoding. By augmenting the reconstruction loss with a semantic loss, the two deep neural networks (DNNs) of this encoder-decoder pair are interactively trained with the DNN of the semantic task classifier. This approach effectively captures the latent feature space and reliably transfers compressed feature vectors with a small number of channel uses while keeping the semantic loss low. We identify the multi-domain security vulnerabilities of using the DNNs for semantic communications. Based on adversarial machine learning, we introduce test-time (targeted and non-targeted) adversarial attacks on the DNNs by manipulating their inputs at different stages of semantic communications. As a computer vision attack, small perturbations are injected to the images at the input of the transmitter's encoder. As a wireless attack, small perturbations signals are transmitted to interfere with the input of the receiver's decoder. By launching these stealth attacks individually or more effectively in a combined form as a multi-domain attack, we show that it is possible to change the semantics of the transferred information even when the reconstruction loss remains low. These multi-domain adversarial attacks pose as a serious threat to the semantics of information transfer (with larger impact than conventional jamming) and raise the need of defense methods for the safe adoption of semantic communications.

通过从大型天线移动到用于软件定义的无线系统的天线表面，可重新配置的智能表面（RISS）依赖于单元电池的阵列，以控制信号的散射和反射轮廓，减轻传播损耗和多路径衰减，从而改善覆盖范围和光谱效率。在本文中，在RIS存在下考虑了隐蔽的通信。虽然RIS升高了持续的传动，但是预期接收器和窃听者都可以单独尝试使用自己的深神经网络（DNN）分类器来检测该传输。 RIS交互向量是通过平衡将发送信号聚焦到接收器的两个（潜在冲突）目标而设计的，并将发送的信号远离窃听器。为了提高封面通信，对发射机的信号添加对抗扰动以欺骗窃听器的分类器，同时保持对接收器的影响。来自不同网络拓扑的结果表明，可以共同设计对抗扰动和RIS交互向量，以有效地提高接收器处的信号检测精度，同时降低窃听器的检测精度以实现封面通信。

本文提出了一种新的方法，用于可重新配置智能表面（RIS）和发射器 - 接收器对的联合设计，其作为一组深神经网络（DNN）培训，以优化端到端通信性能接收者。 RIS是一种软件定义的单位单元阵列，其可以根据散射和反射轮廓来控制，以将来自发射机的传入信号集中到接收器。 RIS的好处是通过克服视线（LOS）链路的物理障碍来提高无线通信的覆盖率和光谱效率。 RIS波束码字（从预定义的码本）的选择过程被配制为DNN，而发射器 - 接收器对的操作被建模为两个DNN，一个用于编码器（在发射器）和另一个一个用于AutoEncoder的解码器（在接收器处），通过考虑包括由in之间引起的频道效应。底层DNN共同训练，以最小化接收器处的符号误差率。数值结果表明，所提出的设计在各种基线方案中实现了误差性能的主要增益，其中使用了没有RIS或者将RIS光束的选择与发射器 - 接收器对的设计分离。

本文提出了对基于深度学习的无线信号分类器的信道感知对抗攻击。有一个发射器，发送具有不同调制类型的信号。每个接收器使用深神经网络以将其超空气接收信号分类为调制类型。与此同时，对手将对手扰动（受到电力预算的影响）透射到欺骗接收器，以在作为透射信号叠加和对抗扰动的叠加接收的分类信号中进行错误。首先，当在设计对抗扰动时不考虑通道时，这些逃避攻击被证明会失败。然后，通过考虑来自每个接收器的对手的频道效应来提出现实攻击。在示出频道感知攻击是选择性的（即，它只影响扰动设计中的信道中考虑的接收器），通过制作常见的对抗扰动来呈现广播对抗攻击，以在不同接收器处同时欺骗分类器。通过占通道，发射机输入和分类器模型可用的不同信息，将调制分类器对过空中侵犯攻击的主要脆弱性。最后，引入了基于随机平滑的经过认证的防御，即增加了噪声训练数据，使调制分类器鲁棒到对抗扰动。