Tracy Camp
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tracy Camp has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Allyson Kennedy
National Science Foundation, Washington, DC, USA
2 shared publications - Colleen M. Lewis
Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, Illinois, USA
2 shared publications - Dorian Arnold
Emory University, Atlanta, GA, USA
2 shared publications - Luther A. Tychonievich
University of Illinois Urbana-Champaign, Urbana, IL, USA
2 shared publications - Manuel Angel Pérez Quiñones
University of North Carolina at Charlotte, Charlotte, NC, USA
2 shared publications - Mary Hall
University of Utah
2 shared publications
Latest Publications
- Open Access
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1709
Launching an Educational Vision to Expand Leadership, Understanding, and Progress in Artificial Intelligence (LEVEL UP AI)
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1709
Open AccessLaunching an Educational Vision to Expand Leadership, Understanding, and Progress in Artificial Intelligence (LEVEL UP AI)
- 30 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 925-930
Generalizing Machine Learning Models for Zero-Day Encrypted Messaging Applications
Access to fully-labeled mobile network traffic data is challenging to come by and harder still to keep up-to-date. Utilizing positive and unlabeled (PU) learning allows us to focus on labeling only a small subset of classes while using large amounts of unlabeled data. Furthermore, the positive labeled data for these few essential classes can be combined to represent a shared genre and then used to classify other applications belonging to the same genre, even when no training data is present for those new applications. We show that PU learning models, trained on several of the most popular encrypted messaging applications on the Android OS, can effectively detect zero-day applications, i.e., those that were not present during the training of the models, with a combined average accuracy of almost 60%. In contrast, random guessing yields less than 1%.
- 30 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 925-930
Generalizing Machine Learning Models for Zero-Day Encrypted Messaging Applications
Access to fully-labeled mobile network traffic data is challenging to come by and harder still to keep up-to-date. Utilizing positive and unlabeled (PU) learning allows us to focus on labeling only a small subset of classes while using large amounts of unlabeled data. Furthermore, the positive labeled data for these few essential classes can be combined to represent a shared genre and then used to classify other applications belonging to the same genre, even when no training data is present for those new applications. We show that PU learning models, trained on several of the most popular encrypted messaging applications on the Android OS, can effectively detect zero-day applications, i.e., those that were not present during the training of the models, with a combined average accuracy of almost 60%. In contrast, random guessing yields less than 1%.
- Open Access
- 6 March 2022
- Published by Association for Computing Machinery (ACM)
- p. 1178
Departmental BPC Plans 1 - Getting Started
- 6 March 2022
- Published by Association for Computing Machinery (ACM)
- p. 1178
Open AccessDepartmental BPC Plans 1 - Getting Started
- Open Access
- 6 March 2022
- Published by Association for Computing Machinery (ACM)
- p. 1178
Departmental BPC Plans 2 - Finalizing your Plan
- 6 March 2022
- Published by Association for Computing Machinery (ACM)
- p. 1178
Open AccessDepartmental BPC Plans 2 - Finalizing your Plan
- Open Access
- 26 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 528-534
Applying NCWIT Protocol to Broaden Participation in Computing
- 26 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 528-534
Open AccessApplying NCWIT Protocol to Broaden Participation in Computing
- 4 August 2019
- Published by Springer Nature
- p. 109-121
Training a RoboCup Striker Agent via Transferred Reinforcement Learning
- 4 August 2019
- Published by Springer Nature
- p. 109-121
Training a RoboCup Striker Agent via Transferred Reinforcement Learning
- Open Access
- 18 April 2017
- Published by Association for Computing Machinery (ACM) in GetMobile: Mobile Computing and Communications
- Vol. 20 (4) , 12-16
10 Years of Networking Networking Women
Networking Networking Women (N2Women) celebrated its 10-year anniversary at the fifth N2Women Workshop co-located with MobiCom 2016. Founded in 2006 by Tracy Camp and Wendi Heinzelman, N2Women is a discipline-specific community for researchers in the communications and networking field. The main goal of N2Women is to foster connections among the underrepresented women in computer networking and related research fields. N2Women allows women to connect with other women who share the same research interests, who attend the same conferences, who face the same career hurdles, and who share common career objectives.
- 18 April 2017
- Published by Association for Computing Machinery (ACM) in GetMobile: Mobile Computing and Communications
- Vol. 20 (4) , 12-16
Open Access10 Years of Networking Networking Women
Networking Networking Women (N2Women) celebrated its 10-year anniversary at the fifth N2Women Workshop co-located with MobiCom 2016. Founded in 2006 by Tracy Camp and Wendi Heinzelman, N2Women is a discipline-specific community for researchers in the communications and networking field. The main goal of N2Women is to foster connections among the underrepresented women in computer networking and related research fields. N2Women allows women to connect with other women who share the same research interests, who attend the same conferences, who face the same career hurdles, and who share common career objectives.
- Open Access
- 22 November 2010
- Published by Association for Computing Machinery (ACM) in ACM SIGMOBILE Mobile Computing and Communications Review
- Vol. 14 (4) , 34-36
SMOOTH
In addition to being realistic, a mobility model should be easy to understand and use. Unfortunately, most of the simple mobility models proposed thus far are not realistic and most of the realistic mobility models proposed thus far are not simple to use. In this work, we present SMOOTH, a new mobility model that is realistic and simple to use. SMOOTH imitates a recently published mobility model, SLAW, that is realistic but not simple to use. While SLAW was constructed by extracting statistical features of real human movement, it has input parameters that are very complex to set. SMOOTH, on the other hand, is realistic (as SMOOTH is based on the real GPS traces used by SLAW) and is simple to use (as SMOOTH avoids SLAW's complex input parameter.
- 22 November 2010
- Published by Association for Computing Machinery (ACM) in ACM SIGMOBILE Mobile Computing and Communications Review
- Vol. 14 (4) , 34-36
Open AccessSMOOTH
In addition to being realistic, a mobility model should be easy to understand and use. Unfortunately, most of the simple mobility models proposed thus far are not realistic and most of the realistic mobility models proposed thus far are not simple to use. In this work, we present SMOOTH, a new mobility model that is realistic and simple to use. SMOOTH imitates a recently published mobility model, SLAW, that is realistic but not simple to use. While SLAW was constructed by extracting statistical features of real human movement, it has input parameters that are very complex to set. SMOOTH, on the other hand, is realistic (as SMOOTH is based on the real GPS traces used by SLAW) and is simple to use (as SMOOTH avoids SLAW's complex input parameter.
- 14 March 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 57 (2) , 1272-1284
A Novel Location Relay Selection Scheme for ALLIANCES
Allow improved access in the network via cooperation and energy savings (ALLIANCES) is a recently proposed cooperative random access protocol for wireless networks that capitalizes on the broadcast nature of the wireless channel. When a collision occurs, a set of nodes forms an alliance and retransmits the collision signal that they heard. The initial collision and retransmissions provide the diversity that is exploited to resolve collisions and, thus, attain high throughput. In this paper, we modify the original model to include node location information. We derive pair-wise error probability (PEP) under a Rayleigh flat-fading channel and a power-law attenuation environment. Based on the PEP analysis, we propose a location relay selection scheme that achieves significant bit-error-rate gains as compared to the random relay selection scheme in the original ALLIANCES.
- 14 March 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 57 (2) , 1272-1284
A Novel Location Relay Selection Scheme for ALLIANCES
Allow improved access in the network via cooperation and energy savings (ALLIANCES) is a recently proposed cooperative random access protocol for wireless networks that capitalizes on the broadcast nature of the wireless channel. When a collision occurs, a set of nodes forms an alliance and retransmits the collision signal that they heard. The initial collision and retransmissions provide the diversity that is exploited to resolve collisions and, thus, attain high throughput. In this paper, we modify the original model to include node location information. We derive pair-wise error probability (PEP) under a Rayleigh flat-fading channel and a power-law attenuation environment. Based on the PEP analysis, we propose a location relay selection scheme that achieves significant bit-error-rate gains as compared to the random relay selection scheme in the original ALLIANCES.
- 1 October 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21556806,p. 256-266
Two Standards for Rigorous MANET Routing Protocol Evaluation
In this paper we look at issues with the simulation of generic mobile ad hoc network (MANET) routing protocols. MANET simulation-based research is an involved process driven by the scenarios used in the simulations. Scenarios must be properly constructed in order to be effective in evaluating the performance of generic MANET routing protocols. For example, in scenarios with a low average hop count, little routing is needed, and poor protocols might appear successful. On the other hand, in scenarios with a high degree of partitioning, many pairs of nodes have no usable route between them, and good protocols might appear unsuccessful. Many standards are needed to establish rigorous evaluations for MANET simulation research, from simulation scenario standards to random number generator standards to results analysis standards. We do not attempt to standardize all of these areas. We do, however, propose two standards that should be employed to ensure long routes are available and used in the evaluation of generic MANET routing protocols. That is, we qualify a simulation scenario to be used for rigorous generic MANET routing protocol evaluation, based on the scenario's average shortest-path hop count and its amount of network partitioning. We construct several simulation scenarios that meet our two standards, using example metric values for our two standards. We note that our method can be modified to generate scenarios with different metric values that a researcher finds appropriate
- 1 October 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21556806,p. 256-266
Two Standards for Rigorous MANET Routing Protocol Evaluation
In this paper we look at issues with the simulation of generic mobile ad hoc network (MANET) routing protocols. MANET simulation-based research is an involved process driven by the scenarios used in the simulations. Scenarios must be properly constructed in order to be effective in evaluating the performance of generic MANET routing protocols. For example, in scenarios with a low average hop count, little routing is needed, and poor protocols might appear successful. On the other hand, in scenarios with a high degree of partitioning, many pairs of nodes have no usable route between them, and good protocols might appear unsuccessful. Many standards are needed to establish rigorous evaluations for MANET simulation research, from simulation scenario standards to random number generator standards to results analysis standards. We do not attempt to standardize all of these areas. We do, however, propose two standards that should be employed to ensure long routes are available and used in the evaluation of generic MANET routing protocols. That is, we qualify a simulation scenario to be used for rigorous generic MANET routing protocol evaluation, based on the scenario's average shortest-path hop count and its amount of network partitioning. We construct several simulation scenarios that meet our two standards, using example metric values for our two standards. We note that our method can be modified to generate scenarios with different metric values that a researcher finds appropriate