In the rapidly expanding landscape of Large Language Model (LLM) applications, real-time output streaming has become the dominant interaction paradigm. While this enhances user experience, recent research reveals that it exposes a non-trivial attack surface through network side-channels. Adversaries can exploit patterns in encrypted traffic to infer sensitive information and reconstruct private conversations. In response, LLM providers and third-party services are deploying defenses such as traffic padding and obfuscation to mitigate these vulnerabilities. This paper starts by presenting a systematic analysis of contemporary side-channel defenses in mainstream LLM applications, with a focus on services from vendors like OpenAI and DeepSeek. We identify and examine seven representative deployment scenarios, each incorporating active/passive mitigation techniques. Despite these enhanced security measures, our investigation uncovers significant residual information that remains vulnerable to leakage within the network traffic. Building on this discovery, we introduce NetEcho, a novel, LLM-based framework that comprehensively unleashes the network side-channel risks of today's LLM applications. NetEcho is designed to recover entire conversations -- including both user prompts and LLM responses -- directly from encrypted network traffic. It features a deliberate design that ensures high-fidelity text recovery, transferability across different deployment scenarios, and moderate operational cost. In our evaluations on medical and legal applications built upon leading models like DeepSeek-v3 and GPT-4o, NetEcho can recover avg $\sim$70\% information of each conversation, demonstrating a critical limitation in current defense mechanisms. We conclude by discussing the implications of our findings and proposing future directions for augmenting network traffic security.
翻译:在大型语言模型(LLM)应用快速扩张的背景下,实时输出流式传输已成为主流的交互范式。尽管这提升了用户体验,但近期研究表明,该范式通过网络侧信道暴露了不容忽视的攻击面。攻击者可利用加密流量中的模式推断敏感信息并重建私人对话。对此,LLM提供商及第三方服务正部署流量填充与混淆等防御措施以缓解此类漏洞。本文首先系统分析了主流LLM应用中的当代侧信道防御方案,重点关注OpenAI、DeepSeek等厂商的服务。我们识别并考察了七种代表性部署场景,每种场景均包含主动/被动缓解技术。尽管存在这些增强的安全措施,我们的研究发现网络流量中仍存在大量易泄露的残余信息。基于此发现,我们提出了NetEcho——一种基于LLM的新型框架,全面揭示了当前LLM应用的网络侧信道风险。NetEcho旨在直接从加密网络流量中恢复完整对话(包括用户提示词与LLM响应),其精心设计的架构确保了高保真文本恢复能力、跨部署场景的可迁移性以及适中的运行成本。我们在基于DeepSeek-v3、GPT-4o等领先模型构建的医疗与法律应用场景中进行评估,NetEcho平均可恢复约70%的对话信息,这揭示了当前防御机制的关键局限。最后,我们讨论了研究发现的潜在影响,并对增强网络流量安全的未来方向提出建议。