语义通信的意外对抗鲁棒性
Unanticipated Adversarial Robustness of Semantic Communication
AI总结:
本文挑战了语义通信易受对抗扰动的普遍观点,发现其具有超越传统分离源信道编码系统的意外对抗鲁棒性,通过理论分析和实验验证其优越性。
摘要:
语义通信,通过深度联合源信道编码(DeepJSCC)实现,广泛被认为继承了深度学习对对抗扰动的脆弱性。本文挑战这一主流观点,揭示了一个反直觉的发现:语义通信系统表现出未预见的对抗鲁棒性,其鲁棒性可超过传统分离源信道编码系统。在理论方面,我们建立了最小攻击功率以引起目标失真的一般界限,通过利用Lipschitz光滑性克服了高度非线性的DeepJSCC模型的分析不可行性。我们证明了隐含正则化从噪声训练迫使解码器光滑性,这一属性本质上提供了对抗攻击的内置保护。为了实现严格和公平的比较,我们开发了两种新的攻击方法,解决了之前未探索的漏洞:一种结构感知的脆弱集攻击,首次利用LDPC码的图论漏洞以最小能量诱导解码失败;另一种渐进梯度上升攻击,利用DeepJSCC的可微性高效地找到最小功率扰动。设计此类攻击具有挑战性,因为传统系统缺乏梯度信息,而语义系统需要在高维非凸空间中导航;我们的方法填补了文献中的关键空白。广泛的实验表明,语义通信需要多达14-16倍的攻击功率才能达到传统系统的相同失真,经验上证实了其优越的鲁棒性。
英文摘要:
Semantic communication, enabled by deep joint source-channel coding (DeepJSCC), is widely expected to inherit the vulnerability of deep learning to adversarial perturbations. This paper challenges this prevailing belief and reveals a counterintuitive finding: semantic communication systems exhibit unanticipated adversarial robustness that can exceed that of classical separate source-channel coding systems. On the theoretical front, we establish fundamental bounds on the minimum attack power required to induce a target distortion, overcoming the analytical intractability of highly nonlinear DeepJSCC models by leveraging Lipschitz smoothness. We prove that the implicit regularization from noisy training forces decoder smoothness, a property that inherently provides built-in protection against adversarial attacks. To enable rigorous and fair comparison, we develop two novel attack methodologies that address previously unexplored vulnerabilities: a structure-aware vulnerable set attack that, for the first time, exploits graph-theoretic vulnerabilities in LDPC codes to induce decoding failure with minimal energy, and a progressive gradient ascent attack that leverages the differentiability of DeepJSCC to efficiently find minimum-power perturbations. Designing such attacks is challenging, as classical systems lack gradient information while semantic systems require navigating high-dimensional, non-convex spaces; our methods fill these critical gaps in the literature. Extensive experiments demonstrate that semantic communication requires up to $14$-$16\times$ more attack power to achieve the same distortion as classical systems, empirically substantiating its superior robustness.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。