Fitness tracking social networks such as Strava allow users to record sports activities and share them publicly. Sharing encourages peer interaction but also constitutes a risk, because an activity's start or finish may inadvertently reveal privacy-sensitive locations such as a home or workplace. To mitigate this risk, networks introduced endpoint privacy zones (EPZs), which hide track portions around protected locations. In this paper, we show that EPZ implementations of major services remain vulnerable to inference attacks that significantly reduce the effective anonymity provided by the EPZ, and even reveal the protected location. Our attack leverages distance information leaked in activity metadata, street grid data, and the locations of the entry points into the EPZ. This yields a constrained search space where we use regression analysis to predict protected locations. Our evaluation on 1.4 million Strava activities shows that our attack discovers the protected location for up to 85% of EPZs. Larger EPZs reduce the performance of our attack, while geographically dispersed activities in sparser street grids yield better performance. We propose six countermeasures, that, however, come with a usability trade-off, and responsibly disclosed our findings and countermeasures to the major networks.

We explore how data modification can enhance privacy by examining the connection between data modification and machine learning. Specifically, machine learning “meets” data modification in two ways. First, data modification can protect the data that is used to train machine learning models focusing it on the intended use and inhibiting unwanted inference. Second, machine learning can provide new ways of creating modified data. In this chapter, we discuss data modification approaches, applied during data pre-processing, that are suited for online data sharing scenarios. Specifically, we define two scenarios “User data sharing” and “Data set sharing” and describe the threat models associated with each scenario and related privacy threats. We then survey the landscape of privacy-enhancing data modification techniques that can be used to counter these threats. The picture that emerges is that data modification approaches hold promise to enhance privacy, and can be used alongside of conventional cryptographic approaches. We close with an outlook on future directions focusing on new types of data, the relationship among privacy, and the importance of taking an interdisciplinary approach to data modification for privacy enhancement.

This chapter contributes to the ongoing discussion of strengthening security by applying AI techniques in the scope of intrusion detection. The focus is set on open-world detection of attacks through data-driven network traffic analysis. This research topic is complementary to the earlier chapter on intelligent malware detection. In this chapter, we revisit the foundations of machine learning-based solutions for network security, which aim to make network defense tools more autonomous, adaptive, proactive and responsive. Specifically, we give a comprehensive introduction to the research on anomaly detection for network intrusion detection – that is, defensive schemes that do not assume complete prior knowledge of malicious patterns and instead learn the notion of normality from benign traffic. Along with outlining the recent advances in the field, we provide insights and reflect on the current limitations and research challenges. Therefore, this chapter presents compelling research opportunities to advance machine learning techniques in network security and push the boundaries of open-world network intrusion detection.