More Like this

1. Identifying UAV Swarm Command Methods and Individual Craft Roles Using Only Passive Sensing

   https://doi.org/10.1109/CSCI49370.2019.00199  

   Meredith, Jonathan; Straub, Jeremy; Bernard, Benjamin (December 2019, Proceedings of the 2019 International Conference on Computational Science and Computational Intelligence (CSCI))

   Anti-drone technologies that attack drone clusters or swarms autonomous command technologies may need to identify the type of command system being utilized and the various roles of particular UAVs within the system. This paper presents a set of algorithms to identify what swarm command method is being used and the role of particular drones within a swarm or cluster of UAVs utilizing only passive sensing techniques (which cannot be detected). A testing configuration for validating the algorithms is also discussed. © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 

   more » « less
2. Creating Simple Adversarial Examples for Speech Recognition Deep Neural Networks

   https://doi.org/10.1109/MASSW.2019.00018  

   Redden, Nathaniel; Bernard, Ben; Straub, Jeremy (November 2019, Proceedings of the 2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops (MASSW))

   The use of deep neural networks for speech recognition and recognizing speech commands continues to grow. This necessitates an understanding of the security risks that goes along with this technology. This paper analyzes the ability to interfere with the performance of neural networks for speech pattern recognition. With the methods proposed herein, it is a simple matter to create adversarial data by overlaying audio of a command at a fairly unnoticeable amplitude. This causes the neural network to lose around 20% accuracy and misidentify commands for other commands with an average to high confidence value. Such an attack is virtually undetectable to the human ear. © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 

   more » « less
3. Use of Bash History Novelty Detection for Identification of Similar Source Attack Generation

   Hance, Jack; Straub, Jeremy (January 2021, Proceedings of the 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom))

   null (Ed.)

   When a cyberattack occurs, tracking the attack back to an actual individual person can be problematic. Even identifying the workstation or device that it originated from does not necessarily identify the attacker, as the attacking device could, itself, be compromised. A system to determine whether activities that occur are from the same user or not facilitates forensic analysis as well as the detection of concurrent attacks from different devices by the same user. This paper proposes a system for identifying attackers based on behaviors expressed via their use of the Bash command line interface, the most common shell on Linux distributions. Prior systems were limited by issues such as requiring labeled user data which is difficult to acquire or not being specific enough to monitor individual persons. The approach proposed herein does not require labeled data and is specific enough to target individual users. The proposed system analyzes the level of variance between commands used and calculates an anomaly score for each given command. It uses these anomaly scores to compare Bash history sets together to identify if they were created by the same user. © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 

   more » « less
4. Manually Classified Real and Fake News Articles

   https://doi.org/10.1109/CSCI49370.2019.00262  

   Snell, Nicholas; Fleck, William; Traylor, Terry; Straub, Jeremy (December 2019, Proceedings of the 2019 International Conference on Computational Science and Computational Intelligence (CSCI))

   News articles that are written with an intent to deliberately deceive or manipulate readers are inherently problematic. These so-called 'fake news' articles are believed to have contributed to election manipulation and even resulted in severe injury and death, by actions that they have triggered. Identifying intentionally deceptive and manipulative news article and alerting human readers is key to mitigating the damage that they can produce. The dataset presented in this paper includes manually identified and classified news stories that can be used for the training and testing of classification systems that identify legitimate versus fake and manipulative news stories. © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 

   more » « less
5. Graphics Card Based Fuzzing

   https://doi.org/10.1109/MASSW.2019.00029  

   Mower, Ryan; Bernard, Ben; Straub, Jeremy (November 2019, Proceedings of the 2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops (MASSW))

   Fuzzing is the art of creating data and using that generated data as input for a target program. The goal behind this is to crash the program in a manner that can be analyzed and exploited. Software developers are able to benefit from fuzzers, as they can patch the discovered vulnerabilities before an attacker exploits them. Programs are becoming larger and require improved fuzzers to keep up with the increased attack surface. Most innovations in fuzzer development are software related and provide better path coverage or data generation. This paper proposes creating a fuzzer that is designed to utilize a dedicated graphics card's graphics processing unit (GPU) instead of the standard processor. Much of the code within the fuzzer is parallelizable, meaning the graphics card could potentially process it in a much more efficient manner. The effectiveness of GPU fuzzing is assessed herein. © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 

   more » « less