Dan S. Wallach

Daniel Song, Jisheng Zhao, Michael Burke et al.

Tizen is a new Linux-based open source platform for consumer devices including smartphones, televisions, vehicles, and wearables. While Tizen provides kernel-level mandatory policy enforcement, it has a large collection of libraries, implemented in a mix of C and C++, which make their own security checks. In this research, we describe the design and engineering of a static analysis engine which drives a full information flow analysis for apps and a control flow analysis for the full library stack. We implemented these static analyses as extensions to LLVM, requiring us to improve LLVM's native analysis features to get greater precision and scalability, including knotty issues like the coexistence of C++ inheritance with C function pointer use. With our tools, we found several unexpected behaviors in the Tizen system, including paths through the system libraries that did not have inline security checks. We show how our tools can help the Tizen app store to verify important app properties as well as helping the Tizen development process avoid the accidental introduction of subtle vulnerabilities.

Clayton Drazner, Nikola Đuza, Hugo Jonker et al.

We investigate adblocking filters and the extent to which websites and advertisers react when their content is impacted by these filters. We collected data daily from the Alexa Top-5000 web sites for 120 days, and from specific sites that newly appeared in filter lists for 140 days. By evaluating how long a filter rule triggers on a website, we can gauge how long it remains effective. We matched websites with both a regular adblocking filter list (EasyList) and with a specialized filter list that targets anti-adblocking logic (Nano Defender). From our data, we observe that the effectiveness of the EasyList adblocking filter decays a modest 0.13\% per day, and after around 80 days seems to stabilize. We found no evidence for any significant decay in effectiveness of the more specialized, but less widely used, anti-adblocking removal filters.

Dan S. Wallach

A recent debate among election experts has considered whether electronic ballot marking devices (BMDs) have adequate security against the risks of malware. A malicious BMD might produce a printed ballot that disagrees with a voter's actual intent, with the hope that voters would be unlikely to detect this subterfuge. This essay considers how an election administrator can create reasonable auditing procedures to gain confidence that their fleet of BMDs is operating correctly, allowing voters to benefit from the usability and accessibility features of BMDs while the overall election still benefits from the same security and reliability properties we expect from hand-marked paper ballots.

Matthew Bernhard, Josh Benaloh, J. Alex Halderman et al.

Elections seem simple---aren't they just counting? But they have a unique, challenging combination of security and privacy requirements. The stakes are high; the context is adversarial; the electorate needs to be convinced that the results are correct; and the secrecy of the ballot must be ensured. And they have practical constraints: time is of the essence, and voting systems need to be affordable and maintainable, and usable by voters, election officials, and pollworkers. It is thus not surprising that voting is a rich research area spanning theory, applied cryptography, practical systems analysis, usable security, and statistics. Election integrity involves two key concepts: convincing evidence that outcomes are correct and privacy, which amounts to convincing assurance that there is no evidence about how any given person voted. These are obviously in tension. We examine how current systems walk this tightrope.

Murat Moran, Dan S. Wallach

We present the first automated privacy analysis of STAR-Vote, a real world voting system design with sophisticated "end-to-end" cryptography, using FDR and ProVerif. We also evaluate the effectiveness of these tools. Despite the complexity of the voting system, we were able to verify that our abstracted formal model of STAR-Vote provides ballot-secrecy using both formal approaches. Notably, ProVerif is radically faster than FDR, making it more suitable for rapid iteration and refinement of the formal model.

M. Sadegh Riazi, Beidi Chen, Anshumali Shrivastava et al.

In Near-Neighbor Search (NNS), a new client queries a database (held by a server) for the most similar data (near-neighbors) given a certain similarity metric. The Privacy-Preserving variant (PP-NNS) requires that neither server nor the client shall learn information about the other party's data except what can be inferred from the outcome of NNS. The overwhelming growth in the size of current datasets and the lack of a truly secure server in the online world render the existing solutions impractical; either due to their high computational requirements or non-realistic assumptions which potentially compromise privacy. PP-NNS having query time {\it sub-linear} in the size of the database has been suggested as an open research direction by Li et al. (CCSW'15). In this paper, we provide the first such algorithm, called Secure Locality Sensitive Indexing (SLSI) which has a sub-linear query time and the ability to handle honest-but-curious parties. At the heart of our proposal lies a secure binary embedding scheme generated from a novel probabilistic transformation over locality sensitive hashing family. We provide information theoretic bound for the privacy guarantees and support our theoretical claims using substantial empirical evidence on real-world datasets.

Theodore Book, Dan S. Wallach

Advertising, long the financial mainstay of the web ecosystem, has become nearly ubiquitous in the world of mobile apps. While ad targeting on the web is fairly well understood, mobile ad targeting is much less studied. In this paper, we use empirical methods to collect a database of over 225,000 ads on 32 simulated devices hosting one of three distinct user profiles. We then analyze how the ads are targeted by correlating ads to potential targeting profiles using Bayes' rule and Pearson's chi squared test. This enables us to measure the prevalence of different forms of targeting. We find that nearly all ads show the effects of application- and time-based targeting, while we are able to identify location-based targeting in 43% of the ads and user-based targeting in 39%.

Yue Liu, David R. Bild, Robert P. Dick et al.

Wireless networks are vulnerable to Sybil attacks, in which a malicious node poses as many identities in order to gain disproportionate influence. Many defenses based on spatial variability of wireless channels exist, but depend either on detailed, multi-tap channel estimation - something not exposed on commodity 802.11 devices - or valid RSSI observations from multiple trusted sources, e.g., corporate access points - something not directly available in ad hoc and delay-tolerant networks with potentially malicious neighbors. We extend these techniques to be practical for wireless ad hoc networks of commodity 802.11 devices. Specifically, we propose two efficient methods for separating the valid RSSI observations of behaving nodes from those falsified by malicious participants. Further, we note that prior signalprint methods are easily defeated by mobile attackers and develop an appropriate challenge-response defense. Finally, we present the Mason test, the first implementation of these techniques for ad hoc and delay-tolerant networks of commodity 802.11 devices. We illustrate its performance in several real-world scenarios.

Theodore Book, Dan S. Wallach

A growing concern with advertisement libraries on Android is their ability to exfiltrate personal information from their host applications. While previous work has looked at the libraries' abilities to measure private information on their own, advertising libraries also include APIs through which a host application can deliberately leak private information about the user. This study considers a corpus of 114,000 apps. We reconstruct the APIs for 103 ad libraries used in the corpus, and study how the privacy leaking APIs from the top 20 ad libraries are used by the applications. Notably, we have found that app popularity correlates with privacy leakage; the marginal increase in advertising revenue, multiplied over a larger user base, seems to incentivize these app vendors to violate their users' privacy.

Theodore Book, Martha Witick, Dan S. Wallach

In this paper, we demonstrate that it is possible to automatically generate fingerprints for various web server types using multifactor Bayesian inference on randomly selected servers on the Internet, without building an a priori catalog of server features or behaviors. This makes it possible to conclusively study web server distribution without relying on reported (and variable) version strings. We gather data by sending a collection of specialized requests to 110,000 live web servers. Using only the server response codes, we then train an algorithm to successfully predict server types independently of the server version string. In the process, we note several distinguishing features of current web infrastructure.

Theodore Book, Adam Pridgen, Dan S. Wallach

This paper investigates changes over time in the behavior of Android ad libraries. Taking a sample of 100,000 apps, we extract and classify the ad libraries. By considering the release dates of the applications that use a specific ad library version, we estimate the release date for the library, and thus build a chronological map of the permissions used by various ad libraries over time. We find that the use of most permissions has increased over the last several years, and that more libraries are able to use permissions that pose particular risks to user privacy and security.

Tao Zhu, David Phipps, Adam Pridgen et al.

Weibo and other popular Chinese microblogging sites are well known for exercising internal censorship, to comply with Chinese government requirements. This research seeks to quantify the mechanisms of this censorship: how fast and how comprehensively posts are deleted.Our analysis considered 2.38 million posts gathered over roughly two months in 2012, with our attention focused on repeatedly visiting "sensitive" users. This gives us a view of censorship events within minutes of their occurrence, albeit at a cost of our data no longer representing a random sample of the general Weibo population. We also have a larger 470 million post sampling from Weibo's public timeline, taken over a longer time period, that is more representative of a random sample. We found that deletions happen most heavily in the first hour after a post has been submitted. Focusing on original posts, not reposts/retweets, we observed that nearly 30% of the total deletion events occur within 5- 30 minutes. Nearly 90% of the deletions happen within the first 24 hours. Leveraging our data, we also considered a variety of hypotheses about the mechanisms used by Weibo for censorship, such as the extent to which Weibo's censors use retrospective keyword-based censorship, and how repost/retweet popularity interacts with censorship. We also used natural language processing techniques to analyze which topics were more likely to be censored.

Peiyou Song, Anhei Shu, Anyu Zhou et al.

The Chinese language poses challenges for natural language processing based on the unit of a word even for formal uses of the Chinese language, social media only makes word segmentation in Chinese even more difficult. In this document we propose a pointillism approach to natural language processing. Rather than words that have individual meanings, the basic unit of a pointillism approach is trigrams of characters. These grams take on meaning in aggregate when they appear together in a way that is correlated over time. Our results from three kinds of experiments show that when words and topics do have a meme-like trend, they can be reconstructed from only trigrams. For example, for 4-character idioms that appear at least 99 times in one day in our data, the unconstrained precision (that is, precision that allows for deviation from a lexicon when the result is just as correct as the lexicon version of the word or phrase) is 0.93. For longer words and phrases collected from Wiktionary, including neologisms, the unconstrained precision is 0.87. We consider these results to be very promising, because they suggest that it is feasible for a machine to reconstruct complex idioms, phrases, and neologisms with good precision without any notion of words. Thus the colorful and baroque uses of language that typify social media in challenging languages such as Chinese may in fact be accessible to machines.