20 citations · 47 across the 19 of their papers we have counts for
19 papers
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
Chace Ashcraft, Ted Staley, Josh Carney +4
Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet da…
Investigating the Treacherous Turn in Deep Reinforcement Learning
Chace Ashcraft, Kiran Karra, Josh Carney +1
The Treacherous Turn refers to the scenario where an artificial intelligence (AI) agent subtly, and perhaps covertly, learns to perform a behavior that benefits itself but is deeme…
Smoothening block rewards: How much should miners pay for mining pools?
Axel Cortes-Cubero, Juan P. Madrigal-Cianci, Kiran Karra +1
The rewards a blockchain miner earns vary with time. Most of the time is spent mining without receiving any rewards, and only occasionally the miner wins a block and earns a reward…
Quantifying Non-linear Dependencies in Blind Source Separation of Power System Signals using Copula Statistics
Pooja Algikar, Lamine Mili, Kiran Karra +2
The dynamics of a power system with a significant presence of renewable energy resources are growing increasingly nonlinear. This nonlinearity is a result of the intermittent natur…
An Agent-Based Model Framework for Utility-Based Cryptoeconomies
Kiran Karra, Tom Mellan, Maria Silva +3
In this paper, we outline a framework for modeling utility-based blockchain-enabled economic systems using Agent Based Modeling (ABM). Our approach is to model the supply dynamics…
Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity
Nathan Drenkow, Alvin Tan, Chace Ashcraft +1
The deployment of machine learning models in safety-critical applications comes with the expectation that such models will perform well over a range of contexts (e.g., a vision mod…
Machine Learning aided Crop Yield Optimization
Chace Ashcraft, Kiran Karra
We present a crop simulation environment with an OpenAI Gym interface, and apply modern deep reinforcement learning (DRL) algorithms to optimize yield. We empirically show that DRL…
SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks
Kiran Karra, Chace Ashcraft, Cash Costello
Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn genera…
Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers
Chace Ashcraft, Kiran Karra
In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents. Our attack centers on what we call in-distribution triggers, which are tri…
Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings
Kiran Karra, Alan McCree
Many modern systems for speaker diarization, such as the recently-developed VBx approach, rely on clustering of DNN speaker embeddings followed by resegmentation. Two problems with…
Probabilistic Load-Margin Assessment using Vine Copula and Gaussian Process Emulation
Yijun Xu, Kiran Karra, Lamine Mili +3
The increasing penetration of renewable energy along with the variations of the loads bring large uncertainties in the power system states that are threatening the security of powe…
The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
Kiran Karra, Chace Ashcraft, Neil Fendley
In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL)…
An Empirical Assessment of the Complexity and Realism of Synthetic Social Contact Networks
Kiran Karra, Samarth Swarup, Justus Graham
We use multiple measures of graph complexity to evaluate the realism of synthetically-generated networks of human activity, in comparison with several stylized network models as we…
On the Effect of Suboptimal Estimation of Mutual Information in Feature Selection and Classification
Kiran Karra, Lamine Mili
This paper introduces a new property of estimators of the strength of statistical association, which helps characterize how well an estimator will perform in scenarios where depend…
Learning Approximate Neural Estimators for Wireless Channel State Information
Timothy J. O'Shea, Kiran Karra, T. Charles Clancy
Estimation is a critical component of synchronization in wireless and signal processing systems. There is a rich body of work on estimator derivation, optimization, and statistical…
Copula Index for Detecting Dependence and Monotonicity between Stochastic Signals
Kiran Karra, Lamine Mili
This paper introduces a nonparametric copula-based index for detecting the strength and monotonicity structure of linear and nonlinear statistical dependence between pairs of rando…
A Copula Statistic for Measuring Nonlinear Multivariate Dependence
Mohsen Ben Hassine, Lamine Mili, Kiran Karra
A new index based on empirical copulas, termed the Copula Statistic (CoS), is introduced for assessing the strength of multivariate dependence and for testing statistical independe…
Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention
Timothy J O'Shea, Kiran Karra, T. Charles Clancy
We address the problem of learning efficient and adaptive ways to communicate binary information over an impaired channel. We treat the problem as reconstruction optimization throu…
GNU Radio Signal Processing Models for Dynamic Multi-User Burst Modems
Timothy J O'Shea, Kiran Karra
This paper presents a modern method for implementing burst modems in GNU Radio. Since burst modems are widely used for multi-user channel access and sharing in non-broadcast radio…