Newest papers

NetGuise: Adversarial Traffic Generation for Early-Stage Classifier Evasion

Binghui Wu, Dinil Mon Divakaran, Mohan Gurusamy · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27456 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

现有的反对流量生成方法往往假定完整的流量、功能层次的扰乱或反复的运行时间反馈,不符合早期执行的局限性,允许低延迟分类,但在现实的流量转移中增加了强度评估的担忧。现有的反对流量生成方法通常假定完整的流量、功能层次的扰乱或反复的运行时间反馈,而不符合早期执行的局限性。我们介绍NetGuise,一个针对两个观察界面下的审查逃避的强度评估框架,i)创建一个仅限于历史的因果界面,即在线包宽度上调节和非负面的延迟行动,ii)以及在带头上造成的八百分之八十的交叉冲击和交叉冲击后,提供

Machine translation (Meta M2M100); the English original follows.

Abstract

Early-stage encrypted traffic classifiers make decisions from only the first few packets of a connection, enabling low-latency classification but raising robustness concerns under realistic traffic morphing. Existing adversarial traffic generation methods often assume complete flows, feature-level perturbations, or iterative runtime feedback, which do not match the constraints of early-stage execution. We present NetGuise, a target-conditioned traffic morphing framework that generates packet-level padding and non-negative delay actions while preserving packet direction, ordering, and packet count and respecting MTU, bandwidth, and latency constraints. We evaluate NetGuise for censorship evasion under two observation interfaces, i) a history-only causal interface for online packet-by-packet execution, ii) and a full-window oracle interface that provides an upper-bound characterization of early-stage morphability. On VANT, NetGuise achieves 33.2% mean targeted evasion under the causal interface versus 82.0% under the oracle interface; on UTMobileNet, the corresponding results are 5.6% and 81.8%. NetGuise outperforms the strongest causal baseline, BAP, on both datasets and, on VANT, reduces bandwidth overhead from 19.80% to 3.02% and generation latency from 37.42 ms/flow to 1.16 ms/flow. Under the oracle interface, it achieves up to 85.7% targeted evasion, retains 43.5% after four rounds of adaptive censor retraining, and maintains 48% under zero-shot cross-environment transfer. Our results show that early-stage classifiers can remain morphable despite high clean accuracy and that robustness evaluation should account for targeted morphability, observation constraints, defender adaptation, and operational network conditions.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Oracle, Network packet, Robustness (evolution), Computer network, Classifier (UML)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange