Website Fingerprinting (WF) attacks aim to infer the websites visited by Tor users by analyzing patterns in encrypted network traffic. However, most existing WF attacks are evaluated on traffic collected in controlled environments with fixed configurations, failing to reflect the complexity and variability of real-world conditions. In practice, traffic is far more dynamic and diverse due to heterogeneous network conditions, the large number of subpages within individual websites, and continuous evolution of website content. These factors increase intra-class variability and induce temporal feature drift, which ultimately degrades the long-term effectiveness of existing attacks. In this paper, we propose TraVerse, an LLM-based representation learning framework designed to achieve robust WF attacks under real-world conditions. TraVerse applies architectural adaptation and large-scale fine-tuning on diverse unlabeled traffic to learn generalizable and resilient representations that remain effective in dynamic and evolving environments. Furthermore, TraVerse integrates a lightweight classifier atop the LLM-derived representations, enabling accurate website identification and efficient few-shot adaptation with minimal model updates. We prototype TraVerse and conduct comprehensive evaluations using real-user traffic. Experimental results show that TraVerse improves Accuracy@3 by an average of 176.3% and weighted F1 by 343.3% over state-of-the-art baselines, while maintaining strong performance throughout a three-month longitudinal evaluation.

Website fingerprinting enables an eavesdropper to determine which websites a user is visiting over an encrypted connection. State-of-the-art website fingerprinting (WF) attacks have demonstrated effectiveness even against Tor-protected network traffic. However, existing WF attacks have critical limitations on accurately identifying websites in multi-tab browsing sessions, where the holistic pattern of individual websites is no longer preserved, and the number of tabs opened by a client is unknown a priori. In this paper, we propose ARES, a novel WF framework natively designed for multi-tab WF attacks. ARES formulates the multi-tab attack as a multi-label classification problem and solves it using the novel Transformer-based models. Specifically, ARES extracts local patterns based on multi-level traffic aggregation features and utilizes the improved self-attention mechanism to analyze the correlations between these local patterns, effectively identifying websites. We implement a prototype of ARES and extensively evaluate its effectiveness using our large-scale datasets collected over multiple months. The experimental results illustrate that ARES achieves optimal performance in several realistic scenarios. Further, ARES remains robust even against various WF defenses.

Machine learning (ML) is promising in accurately detecting malicious flows in encrypted network traffic; however, it is challenging to collect a training dataset that contains a sufficient amount of encrypted malicious data with correct labels. When ML models are trained with low-quality training data, they suffer degraded performance. In this paper, we aim to address a real-world low-quality training dataset problem, namely, detecting encrypted malicious traffic generated by continuously evolving malware. We develop RAPIER+ that fully utilizes different distributions of normal and malicious traffic data in the feature space, where normal data is tightly distributed in a certain area, and the malicious data is scattered over the entire feature space to augment training data for model training. RAPIER+ includes two pre-processing modules to convert traffic into feature vectors and correct label noises. We evaluate our system on two public datasets and one combined dataset. With 1000 samples and 45% noise from each dataset, our system achieves the F1 scores of 0.78, 0.84, and 0.87, respectively, achieving average improvements of 358.5%, 314.0%, and 221.1% over the existing methods, respectively. Furthermore, we evaluate RAPIER+ with a real-world dataset obtained from a security enterprise. RAPIER+ effectively achieves encrypted malicious traffic detection with the best F1 score of 0.81 and improves the F1 score of existing methods by an average of 288.7%.

Most existing DL-based encrypted traffic classification methods suffer performance degradation in real-world deployments due to dynamic network conditions, e.g., network environment changes and traffic obfuscation. Dynamic network conditions cause encrypted traffic to exhibit distinct feature patterns during training and testing phases. To address this issue, we propose MetaTraffic, a novel and general DL training framework built upon meta-learning that enhances the performance of supervised DL models designed for encrypted traffic classification against dynamic network conditions. Our key observation is that the traffic of the same network behaviors share the same semantic features even under different network conditions, which can be considered as stable feature representations. Therefore, MetaTraffic helps DL models learn stable feature representations by minimizing the discrepancies in how the models represent traffic features under different network conditions, thereby achieving robust classification under dynamic network conditions. We implement MetaTraffic based on meta-learning with three innovative facilitate modules to enhance its performance. We evaluate MetaTraffic using three public datasets and three new large-scale encrypted traffic datasets that cover multiple types of network conditions. Experimental results show that, under dynamic multiple types of network conditions, our framework improves the accuracy of DL models by 8.94% and the F1-Macro score by 12.55%, while existing robust training methods decrease the accuracy by 28.85% and the F1-Macro score by 33.52%.

Traffic encryption has been widely adopted to protect the confidentiality and integrity of Internet traffic. However, attackers can also abuse such mechanism to deliver malicious traffic. Particularly, existing methods detecting encrypted malicious traffic are not robust against evasion attacks that manipulate traffic to obfuscate traffic features. Robust detection against evasion attacks remains an open problem. To the end, we develop Wedjat, which utilizes a causal network to model benign packet interactions among relevant flows, such that it recognizes abnormal causality that represents malicious traffic and disrupted causality incurred by evasion attacks. We extensively evaluate Wedjat with millions of flows collected from a real-world enterprise. The experimental results demonstrate that Wedjat achieves an accuracy of 0.957 F1-score when detecting various advanced attacks. Notably, five sophisticated evasion attacks, which have successfully evaded all existing methods, are accurately detected by Wedjat with over 0.915 F1. It demonstrates that Wedjat achieves exceptional robustness against evasions. Meanwhile, Wed- jat maintains an outstanding detection latency, i.e., it can predict each packet in less than 0.125 seconds.

Website Fingerprinting (WF) is a traffic analysis technique that aims to identify websites visited by users through the analysis of encrypted traffic patterns.Existing approaches often exhibit limited robustness against network variability and concept drift, resulting in significant performance degradation under real-world HTTPS conditions.Moreover, these methods typically require large-scale training datasets and substantial computational resources, which further increases the complexity of deployment.In this paper, we propose HOLMES, a novel approach that exploits HTTP version parallelism to extract enhanced application-layer features.These features, including the number of web resources transmitting in various HTTP versions, expose up to 4.28 bits of information-surpassing 98% of previously reported features and demonstrate increased stability across varying network conditions.Complementary to this, we introduce WATSON, a lightweight classification method based on lazy learning, which substantially reduces the dependency on large training datasets.To further enhance the identification accuracy, we incorporate two fingerprint-specific distance metrics that ensure high intra-class similarity.Our experimental evaluation demonstrates that HOLMES & WATSON significantly enhance both robustness and efficiency, achieving an average accuracy of 87.7% with only a single sample per website, marking an improvement of over 15% compared to state-of-the-art methods.

Website Fingerprinting (WF) attacks identify the websites visited by users by performing traffic analysis, compromising user privacy. Particularly, DL-based WF attacks demonstrate impressive attack performance. However, the effectiveness of DL-based WF attacks relies on the collected complete and pure traffic during the page loading, which impacts the practicality of these attacks. The WF performance is rather low under dynamic network conditions and various WF defenses, particularly when the analyzed traffic is only a small part of the complete traffic. In this paper, we propose Holmes, a robust and reliable early-stage WF attack. Holmes utilizes temporal and spatial distribution analysis of website traffic to effectively identify websites in the early stages of page loading. Specifically, Holmes develops adaptive data augmentation based on the temporal distribution of website traffic and utilizes a supervised contrastive learning method to extract the correlations between the early-stage traffic and the pre-collected complete traffic. Holmes accurately identifies traffic in the early stages of page loading by computing the correlation of the traffic with the spatial distribution information, which ensures robust and reliable detection according to early-stage traffic. We extensively evaluate Holmes using six datasets. Compared to nine existing DL-based WF attacks, Holmes improves the F1-score of identifying early-stage traffic by an average of 169.18%. Furthermore, we replay the traffic of visiting real-world dark web websites. Holmes successfully identifies dark web websites when the ratio of page loading on average is only 21.71%, with an average precision improvement of 169.36% over the existing WF attacks.

Website Fingerprinting (WF) attacks can effectively identify the websites visited by Tor clients via analyzing encrypted traffic patterns. Existing attacks focus on identifying different websites, but their accuracy dramatically decreases when applied to identify fine-grained webpages, especially when distinguishing among different subpages of the same website. WebPage Fingerprinting (WPF) attacks face the challenges of highly similar traffic patterns and a much larger scale of webpages. Furthermore, clients often visit multiple webpages concurrently, increasing the difficulty of extracting the traffic patterns of each webpage from the obfuscated traffic. In this paper, we propose Oscar, a WPF attack based on multi-label metric learning that identifies different webpages from obfuscated traffic by transforming the feature space. Oscar can extract the subtle differences among various webpages, even those with similar traffic patterns. In particular, Oscar combines proxy-based and sample-based metric learning losses to extract webpage features from obfuscated traffic and identify multiple webpages. We prototype Oscar and evaluate its performance using traffic collected from 1,000 monitored webpages and over 9,000 unmonitored webpages in the real world. Oscar demonstrates an 88.6% improvement in the multi-label metric Recall@5 compared to the state-of-the-art attacks.

Ternary Content Addressable Memory (TCAM) enables fast lookup and is widely used by routers and switches to support policy-based forwarding. Due to high cost and small capacity, only a small subset of important rules can be cached in TCAM, so determining it is critical to increasing the hit ratio. This is more challenging than traditional caching problems because of complicated rule dependency relationships. Existing works are based on heuristics and they don’t work well under all practical scenarios. Worse still, the lack of fundamental understanding of the design space, complexity, and optimality makes all explorations in mystery. In this paper, we use a modeling-based method to formulate the problem, prove its complexity, and propose DROPS, a dynamic rule caching framework with a much higher hit ratio. In particular, we deduce the rule selection problem into a multi-dimensional rule space transformation problem. Thus, we are no longer limited by using the intrinsic rules; rather, we can transform original rules into “new rules” equivalently without rule dependency. We design non-trivial rule placement and update algorithms and implement them in programmable switches. In the experimental evaluation, we show that our method outperforms all existing methods.

Website fingerprinting enables an eavesdropper to determine which websites a user is visiting over an encrypted connection. State-of-the-art website fingerprinting (WF) attacks have demonstrated effectiveness even against Tor-protected network traffic. However, existing WF attacks have critical limitations on accurately identifying websites in multi-tab browsing sessions, where the holistic pattern of individual websites is no longer preserved, and the number of tabs opened by a client is unknown a priori. In this paper, we propose ARES, a novel WF framework natively designed for multi-tab WF attacks. ARES formulates the multi-tab attack as a multi-label classification problem and solves it using a multi-classifier framework. Each classifier, designed based on a novel transformer model, identifies a specific website using its local patterns extracted from multiple traffic segments. We implement a prototype of ARES and extensively evaluate its effectiveness using our large-scale dataset collected over multiple months (by far the largest multi-tab WF dataset studied in academic papers.) The experimental results illustrate that ARES effectively achieves the multi-tab WF attack with the best F1-score of 0.907. Further, ARES remains robust even against various WF defenses.

Network Function Virtualization (NFV) is a new networking paradigm to enable dynamic network function deployment in networks. Existing studies focused on optimized function deployment and management in NFV. Unfortunately, these studies did not well address the problem of efficient security function enforcement in networks, which is the goal of deploying network functions (NFs), i.e., for real-time security function enforcement on the traffic, since optimal function deployment does not mean efficient security function enforcement on network traffic. In particular, they incurred significant NF enforcement cost. In order to address this issue, in this paper, we propose${\textsf {FuncE}}$that aims to solve the efficient real-time security function enforcement problem by developing unified dynamic flow and function scheduling. We formulate the problem as an integer linear programming problem and prove that it is NP-hard. We tackle the problem by decomposing it and developing heuristics to achieve near-optimal solutions. We conduct comprehensive experiments by using real topologies to demonstrate the effectiveness of the${\textsf {FuncE}}$design. The experimental results demonstrate that${\textsf {FuncE}}$achieves near-optimal network function enforcement, which incurs over 100 times less latency than the existing the optimal solver. In particular, compared to the state-of-art defenses,${\textsf {FuncE}}$processes the same number of candidate flows using over 50% less VNFs, while ensuring the same level of function enforcement.

With increasing demands for more flexible services, the routing policies in enterprise networks become much richer. This has placed a heavy burden to the current router forwarding plane in support of the increasing number of policies, primarily due to the limited capacity in TCAM, which further hinders the development of new network services and applications. The scalable forwarding table structures for enterprise networks have therefore attracted numerous attentions from both academia and industry. To tackle this challenge, in this paper we present the design and implementation of a new forwarding table structure. It separates the functions of TCAM and SRAM, and maximally utilizes the large and flexible SRAM. A set of schemes are progressively designed, to compress storage of forwarding rules, and maintain correctness and achieve line-card speeds of packet forwarding. We further design an incremental update algorithm that allows less access to memory. The proposed scheme is validated and evaluated through a realistic implementation on a commercial router using real datasets. Our proposal can be easily implemented in the existing devices. The evaluation results show that the performance of forwarding tables under the proposed scheme is promising.