Biblio

The widespread use of powerful mobile devices has deeply affected the mix of traffic traversing both the Internet and enterprise networks (with bring-your-own-device policies). Traffic encryption has become extremely common, and the quick proliferation of mobile apps and their simple distribution and update have created a specifically challenging scenario for traffic classification and its uses, especially network-security related ones. The recent rise of Deep Learning (DL) has responded to this challenge, by providing a solution to the time-consuming and human-limited handcrafted feature design, and better clas-sification performance. The counterpart of the advantages is the lack of interpretability of these black-box approaches, limiting or preventing their adoption in contexts where the reliability of results, or interpretability of polices is necessary. To cope with these limitations, eXplainable Artificial Intelligence (XAI) techniques have seen recent intensive research. Along these lines, our work applies XAI-based techniques (namely, Deep SHAP) to interpret the behavior of a state-of-the-art multimodal DL traffic classifier. As opposed to common results seen in XAI, we aim at a global interpretation, rather than sample-based ones. The results quantify the importance of each modality (payload- or header-based), and of specific subsets of inputs (e.g., TLS SNI and TCP Window Size) in determining the classification outcome, down to per-class (viz. application) level. The analysis is based on a publicly-released recent dataset focused on mobile app traffic.

With the rapid development of traffic encryption technology and the continuous emergence of various network services, the classification of encrypted zero-day applications has become a major challenge in network supervision. More seriously, many attackers will utilize zero-day applications to hide their attack behaviors and make attack undetectable. However, there are very few existing studies on zero-day applications. Existing works usually select and label zero-day applications from unlabeled datasets, and these are not true zero-day applications classification. To address the classification of zero-day applications, this paper proposes an Encrypted Zero-day Applications Classification (EZAC) method that combines Convolutional Neural Network (CNN) and K-Means, which can effectively classify zero-day applications. We first use CNN to classify the flows, and for the flows that may be zero-day applications, we use K-Means to divide them into several categories, which are then manually labeled. Experimental results show that the EZAC achieves 97.4% accuracy on a public dataset (CIC-Darknet2020), which outperforms the state-of-the-art methods.

The classification of encrypted traffic has received increased attention by the research community in the cyber-security domains and network management domains. Classification of encrypted traffic can also expose privacy threats as the activities of an user can be detected and identified. This paper investigates the novel application of Time Frequency analysis to encrypted traffic classification. Features extracted from encrypted traffic are normalized and transformed to time series on which different time frequency transforms are applied. In particular, the constant-Q transform (CQT), the Continuous Wavelet Transform and the Wigner-Ville distribution are used. Then, different machine learning algorithms are applied to identify the different types of traffic. This approach is validated with the public ISCX VPN-nonVPN traffic dataset with time-based features extracted from the encrypted traffic. The results show the superior classification performance (evaluated using identification, precision and recall metrics) of the time frequency approach across different machine learning algorithms. Because analysis of encrypted traffic can also generate privacy threats, a technique to obfuscate the time based features and reduce the classification performance is also applied and successfully validated.

Increased use of secure chat and voice/ video apps has transformed the social life. While the benefits and facilitations are seemingly limitless, so are the asscoiacted vulnerabilities and threats. Besides ensuring confidentiality requirements for common users, known facts of non-readable contents over the network make these apps more attractive for criminals. Though access to contents of cryptograhically secure sessions is not possible, network forensics of secure apps can provide interesting information which can be of great help during criminal invetigations. In this paper, we presented a novel framework of profiling the secure chat and voice/ video calling apps which can be employed to extract hidden patterns about the app, information of involved parties, activities of chatting, voice/ video calls, status indications and notifications while having no information of communication protocol of the app and its security architecture. Signatures of any secure app can be developed though our framework and can become base of a large scale solution. Our methodology is considered very important for different cases of criminal investigations and bussiness intelligence solutions for service provider networks. Our results are applicable to any mobile platform of iOS, android and windows.

We consider the setting of HTTP traffic over encrypted tunnels, as used to conceal the identity of websites visited by a user. It is well known that traffic analysis (TA) attacks can accurately identify the website a user visits despite the use of encryption, and previous work has looked at specific attack/countermeasure pairings. We provide the first comprehensive analysis of general-purpose TA countermeasures. We show that nine known countermeasures are vulnerable to simple attacks that exploit coarse features of traffic (e.g., total time and bandwidth). The considered countermeasures include ones like those standardized by TLS, SSH, and IPsec, and even more complex ones like the traffic morphing scheme of Wright et al. As just one of our results, we show that despite the use of traffic morphing, one can use only total upstream and downstream bandwidth to identify – with 98% accuracy - which of two websites was visited. One implication of what we find is that, in the context of website identification, it is unlikely that bandwidth-efficient, general-purpose TA countermeasures can ever provide the type of security targeted in prior work.