Papers Publications

new workshop paper “Leveraging Controlled Information Sharing for Botnet Activity Detection”

We have published a new paper “Leveraging Controlled Information Sharing for Botnet Activity Detection” in the Workshop on Traffic Measurements for Cybersecurity (WTMC 2018) in Budapest, Hungary, co-located with ACM SIGCOMM 2018.

The sensitivity of BotDigger’s detection is im- proved with controlled data sharing. All three domain/IP sets meet or pass the detection threshold.

From the abstract of our paper:

Today’s malware often relies on DNS to enable communication with command-and-control (C&C). As defenses that block traffic improve, malware use sophisticated techniques to hide this traffic, including “fast flux” names and Domain-Generation Algorithms (DGAs). Detecting this kind of activity requires analysis of DNS queries in network traffic, yet these signals are sparse. As bot countermeasures grow in sophistication, detecting these signals increasingly requires the synthesis of information from multiple sites. Yet *sharing security information across organizational boundaries* to date has been infrequent and ad hoc because of unknown risks and uncertain benefits. In this paper, we take steps towards formalizing cross-site information sharing and quantifying the benefits of data sharing. We use a case study on DGA-based botnet detection to evaluate how sharing cybersecurity data can improve detection sensitivity and allow the discovery of malicious activity with greater precision.

The relevant software is open-sourced and freely available at

This paper is joint work between Calvin Ardi and John Heidemann from USC/ISI, with additional support from collaborators and Colorado State University and Los Alamos National Laboratory.

Papers Publications

new conference paper “The Policy Potential of Measuring Internet Outages” at TPRC

We have published a new paper “The Policy Potential of Measuring Internet Outages” in TPRC46, the Research Conference on Communications, Information and Internet Policy, to be presented on September 21, 2018 at the American University, Washington College of Law.

Outages from Hurricane Irma after landfall in Florida on 2017-09-11, observed with Trinocular.

From the abstract of our paper:

Today it is possible to evaluate the reliability of the Internet. Prior approaches to measure network reliability required telecommunications providers reporting the status of their own networks, resulting in limits on the precision, timeliness, and availability of the results. Recent work in Internet measurement has shown that network outages can be observed with active measurements from a few sites, and from passive measurements of network telescopes (large, unused address space) or large network services such as content-delivery networks. We suggest that these kinds of *third-party* observations of network outages can provide data that is precise and timely. We discuss early results of Trinocular, an outage detection system using active probing developed at the University of Southern California. Trinocular has been operating continuously since November 2013, and we provide (at no charge) data covering about 4 million network blocks from around the world. This paper describes some results of Trinocular showing outages in a large U.S. Internet Service Provider, and those resulting from the 2017 Hurricane Irma in Florida. Our data shows the impact of the Broadband America policy for always-on networks, and we discuss how it might be used to address future policy questions and assist in disaster planning and recovery.

Data we describe in this paper is at, with visualizations at

This paper is joint work of John Heideman, Yuri Pradkin, and Guillermo Baltra from USC/ISI, with work carried out as part of LACANIC and DIVOICE projects with DHS S&T/CSD support.

Papers Publications

New workshop paper “IP-Based IoT Device Detection”

We have published a new paper “IP-Based IoT Device Detection” in the Second ACM Workshop on Internet-of-Things Security and Privacy (IoTS&P 2018) in Budapest, Hungary, co-located with SIGCOMM 2018.

IoT devices we detect in use at a campus (Table 3 from [Guo18b])
From the abstract of our  paper:

Recent IoT-based DDoS attacks have exposed how vulnerable the Internet can be to millions of insufficiently secured IoT devices. To understand the risks of these attacks requires
learning about these IoT devices—where are they, how many are there, how are they changing? In this paper, we propose
a new method to find IoT devices in Internet to begin to assess this threat. Our approach requires observations of flow-level network traffic and knowledge of servers run by
the manufacturers of the IoT devices. We have developed our approach with 10 device models by 7 vendors and controlled
experiments. We apply our algorithm to observations from 6 days of Internet traffic at a college campus and partial traffic
from an IXP to detect IoT devices.

We make operational traffic we captured from 10 IoT devices we own public at We also use operational traffic of 21 IoT devices shared by University of New South Wales at

This paper is joint work of Hang Guo and  John Heidemann from USC/ISI.

Papers Publications

new conference paper “Detecting ICMP Rate Limiting in the Internet” in PAM 2018

We have published a new conference “Detecting ICMP Rate Limiting in the Internet” in PAM 2018 (the Passive and Active Measurement Conference) in Berlin, Germany.

Figure 4 from [Guo18a] Confirming a block is rate limited with additional probing
Figure 4 from [Guo18a] confirming a bock is rate limited, comparing experimental results with models of rate-limited and non-rate-limited behavior.
From the abstract of our conference paper:

Comparing model and experimental effects of rate limiting (Figure 4 from [Guo18a] )
ICMP active probing is the center of many network measurements. Rate limiting to ICMP traffic, if undetected, could distort measurements and create false conclusions. To settle this concern, we look systematically for ICMP rate limiting in the Internet. We create FADER, a new algorithm that can identify rate limiting from user-side traces with minimal new measurement traffic. We validate the accuracy of FADER with many different network configurations in testbed experiments and show that it almost always detects rate limiting. With this confidence, we apply our algorithm to a random sample of the whole Internet, showing that rate limiting exists but that for slow probing rates, rate-limiting is very rare. For our random sample of 40,493 /24 blocks (about 2% of the responsive space), we confirm 6 blocks (0.02%!) see rate limiting at 0.39 packets/s per block. We look at higher rates in public datasets and suggest that fall-off in responses as rates approach 1 packet/s per /24 block is consistent with rate limiting. We also show that even very slow probing (0.0001 packet/s) can encounter rate limiting of NACKs that are concentrated at a single router near the prober.

Datasets we used in this paper are all public. ISI Internet Census and Survey data (including it71w, it70w, it56j, it57j and it58j census and survey) are available at ZMap 50-second experiments data are from their WOOT 14 paper and can be obtained from ZMap authors upon request.

This conference report is joint work of Hang Guo and  John Heidemann from USC/ISI.

DNS Papers Presentations Publications

New paper and talk “Enumerating Privacy Leaks in DNS Data Collected above the Recursive” at NDSS DNS Privacy Workshop 2018

Basileal Imana presented the paper “Enumerating Privacy Leaks in DNS Data Collected  above the Recursive” at NDSS DNS Privacy Workshop in San Diego, California, USA on February 18, 2018. Talk slides are available at and paper is available at, or can be found at the DNS privacy workshop page.

From the abstract:

Threat model for enumerating leaks above the recursive (left). Percentage of four categories of queries containing IPv4 addresses in their QNAMEs. (right)

As with any information system consisting of data derived from people’s actions, DNS data is vulnerable to privacy risks. In DNS, users make queries through recursive resolvers to authoritative servers. Data collected below (or in) the recursive resolver directly exposes users, so most prior DNS data sharing focuses on queries above the recursive resolver. Data collected above a recursive resolver has largely been seen as posing a minimal privacy risk since recursive resolvers typically aggregate traffic for many users, thereby hiding their identity and mixing their traffic. Although this assumption is widely made, to our knowledge it has not been verified. In this paper we re-examine this assumption for DNS traffic above the recursive resolver. First, we show that two kinds of information appear in query names above the recursive resolver: IP addresses and sensitive domain names, such as those pertaining to health, politics, or personal or lifestyle information. Second, we examine how often these classes of potentially sensitive names appear in Root DNS traffic, using 48 hours of B-Root data from April 2017.

This is a joint work by Basileal Imana (USC), Aleksandra Korolova (USC) and John Heidemann (USC/ISI).

The DITL dataset (ITL_B_Root-20170411) used in this work is available from DHS IMPACT, the ANT project, and through DNS-OARC.

Papers Publications

new conference paper “A Look at Router Geolocation in Public and Commercial Databases” in IMC 2017

The paper “A Look at Router Geolocation in Public and Commercial Databases” has appeared in the 2017 Internet Measurement Conference (IMC) on November 1-3, 2017 in London, United Kingdom.

From the abstract:

Regional breakdown of the geolocation error for the geolocation databases vs. ground truth data.

Internet measurement research frequently needs to map infrastructure components, such as routers, to their physical locations. Although public and commercial geolocation services are often used for this purpose, their accuracy when applied to network infrastructure has not been sufficiently assessed. Prior work focused on evaluating the overall accuracy of geolocation databases, which is dominated by their performance on end-user IP addresses. In this work, we evaluate the reliability of router geolocation in databases. We use a dataset of about 1.64M router interface IP addresses extracted from the CAIDA Ark dataset to examine the country- and city-level coverage and consistency of popular public and commercial geolocation databases. We also create and provide a ground-truth dataset of 16,586 router interface IP addresses and their city-level locations, and use it to evaluate the databases’ accuracy with a regional breakdown analysis. Our results show that the databases are not reliable for geolocating routers and that there is room to improve their country- and city-level accuracy. Based on our results, we present a set of recommendations to researchers concerning the use of geolocation databases to geolocate routers.

The work in this paper was joint work by Manaf Gharaibeh, Anant Shah, Han Zhang, Christos Papadopoulos (Colorado State University), Brad Huffaker (CAIDA / UC San Diego), and Roya Ensafi (University of Michigan). The findings of this work are highlighted in an APNIC blog post “Should we trust the geolocation databases to geolocate routers?”. The ground truth datasets used in the paper are available via IMPACT.

DNS Papers Publications

new journal paper “Detecting Malicious Activity With DNS Backscatter Over Time” in IEEE/ACM ToN Oct, 2017

The paper “Detecting Malicious Activity With DNS Backscatter Over Time ” appears in EEE/ACM  Transactions on Networking ( Volume: 25, Issue: 5, Oct. 2017 ).

From the abstract:

Network-wide activity is when one computer (the originator) touches many others (the targets). Motives for activity may be benign (mailing lists, CDNs, and research scanning), malicious (spammers and scanners for security vulnerabilities), or perhaps indeterminate (ad trackers). Knowledge of malicious activity may help anticipate attacks, and understanding benign activity may set a baseline or characterize growth. This paper identifies DNS backscatter as a new source of information about network-wide activity. Backscatter is the reverse DNS queries caused when targets or middleboxes automatically look up the domain name of the originator. Queries are visible to the authoritative DNS servers that handle reverse DNS. While the fraction of backscatter they see depends on the server’s location in the DNS hierarchy, we show that activity that touches many targets appear even in sampled observations. We use information about the queriers to classify originator activity using machine learning. Our algorithm has reasonable accuracy and precision (70–80%) as shown by data from three different organizations operating DNS servers at the root or country-level. Using this technique we examine nine months of activity from one authority to identify trends in scanning, identifying bursts corresponding to Heartbleed and broad and continuous scanning of ssh.

This paper furthers our understanding of evolution of malicious network activities from an earlier work that:
(1) Why our machine-learning based classifier (that relies on manually collected labeled data) does not port across physical sites and over time.
(2) Secondly paper recommends how to sustain good learning score over time and provides expected life-time of labeled data.

An excerpt from section III-E (Training Over Time):

Classification (§ III-D) is based on training, yet training accuracy is affected by the evolution of activity—specific examples come and go, and the behavior in each class evolves. Change happens for all classes, but the problem is particularly acute for malicious classes (such as spam) where the adversarial nature of the action forces rapid evolution (see § V).


Some datasets used in this paper can be found here:

Papers Publications

new conference paper “Recursives in the Wild: Engineering Authoritative DNS Servers” in IMC 2017

The paper “Recursives in the Wild: Engineering Authoritative DNS Servers” will appear in the 2017 Internet Measurement Conference (IMC) on November 1-3, 2017 in London, United Kingdom.

Recursive DNS server selection of authoritatives, per continent. (Figure 4 from [Mueller17b].)
From the abstract:

In In Internet Domain Name System (DNS), services operate authoritative name servers that individuals query through recursive resolvers. Operators strive to provide reliability by operating multiple name servers (NS), each on a separate IP address, and by using IP anycast to allow NSes to provide service from many physical locations. To meet their goals of minimizing latency and balancing load across NSes and anycast, operators need to know how recursive resolvers select an NS, and how that interacts with their NS deployments. Prior work has shown some recursives search for low latency, while others pick an NS at random or round robin, but did not examine how prevalent each choice was. This paper provides the first analysis of how recursives select between name servers in the wild, and from that we provide guidance to operators how to engineer their name servers to reach their goals. We conclude that all NSes need to be equally strong and therefore we recommend to deploy IP anycast at every single authoritative.

All datasets used in this paper (but one) are available at .

Papers Publications

new conference paper “Broad and Load-aware Anycast Mapping with Verfploeter” in IMC 2017

The paper “Broad and Load-aware Anycast Mapping with Verfploeter” will appear in the 2017 Internet Measurement Conference (IMC) on November 1-3, 2017 in London, United Kingdom.

From the abstract:

IP anycast provides DNS operators and CDNs with automatic failover and reduced latency by breaking the Internet into catchments, each served by a different anycast site. Unfortunately, understanding and predicting changes to catchments as anycast sites are added or removed has been challenging. Current tools such as RIPE Atlas or commercial equivalents map from thousands of vantage points (VPs), but their coverage can be inconsistent around the globe. This paper proposes Verfploeter, a new method that maps anycast catchments using active probing. Verfploeter provides around 3.8M passive VPs, 430x the 9k physical VPs in RIPE Atlas, providing coverage of the vast majority of networks around the globe. We then add load information from prior service logs to provide calibrated predictions of anycast changes. Verfploeter has been used to evaluate the new anycast deployment for B-Root, and we also report its use of a nine-site anycast testbed. We show that the greater coverage made possible by Verfploeter’s active probing is necessary to see routing differences in regions that have sparse coverage from RIPE Atlas, like South America and China.

Distribution of load across two anycast sites of B-root using Verfploeter.

The work in this paper was joint work by Wouter B. de Vries, Ricardo de O. Schmidt (Univ. of Twente), Wes Hardaker, John Heidemann (USC/ISI), Pieter-Tjerk de Boer and Aiko Pras (Univ. of Twente). The datasets used in the paper are available at

Papers Publications

new conference paper “Does Anycast Hang up on You?” in TMA 2017

The paper “Does Anycast hang up on you?” will appear in the 2017 Conference on Network Traffic Measurement and Analysis (TMA) July 21-23, 2017 in Dublin, Ireland.

In each anycast-based DNS root service, there are about 1% VPs see a route flip happens every one or two observation during a week with an observation interval as 4 minutes. (Figure 2 from [Wei17b]).
From the abstract:

Anycast-based services today are widely used commercially, with several major providers serving thousands of important websites. However, to our knowledge, there has been only limited study of how often anycast fails because routing changes interrupt connections between users and their current anycast site. While the commercial success of anycast CDNs means anycast usually work well, do some users end up shut out of anycast? In this paper we examine data from more than 9000 geographically distributed vantage points (VPs) to 11 anycast services to evaluate this question. Our contribution is the analysis of this data to provide the first quantification of this problem, and to explore where and why it occurs. We see that about 1\% of VPs are anycast unstable, reaching a different anycast site frequently (sometimes every query). Flips back and forth between two sites in 10 seconds are observed in selected experiments for given service and VPs. Moreover, we show that anycast instability is persistent for some VPs—a few VPs never see a stable connections to certain anycast services during a week or even longer. The vast majority of VPs only saw unstable routing towards one or two services instead of instability with all services, suggesting the cause of the instability lies somewhere in the path to the anycast sites. Finally, we point out that for highly-unstable VPs, their probability to hit a given site is constant, which means the flipping are happening at a fine granularity—per packet level, suggesting load balancing might be the cause to anycast routing flipping. Our findings confirm the common wisdom that anycast almost always works well, but provide evidence that a small number of locations in the Internet where specific anycast services are never stable.

This paper is joint work of Lan Wei and John Heidemann.  A pre-print of paper is at, and the datasets from the paper are at