Search Results for author:
Found 101 papers, 36 papers with code
Multi-layer Radial Basis Function Networks for Out-of-distribution Detection
Radial basis function networks (RBFNs) inherently link classification confidence and OOD detection; however, these networks have lost popularity due to the difficult of training them in a multi-layer fashion.
Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation
In this study, we ask the following question: Can Large Language Models (LLMs) potentially generate a new obfuscated assembly code?
Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context
Previous research on LLM vulnerabilities often relied on nonsensical adversarial prompts, which were easily detectable by automated methods.
What Do Machine Learning Researchers Mean by "Reproducible"?
The concern that Artificial Intelligence (AI) and Machine Learning (ML) are entering a "reproducibility crisis" has spurred significant research in the past few years.
Living off the Analyst: Harvesting Features from Yara Rules for Malware Detection
A strategy used by malicious actors is to "live off the land," where benign systems and tools already available on a victim's systems are used and repurposed for the malicious actor's intent.
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
While such algorithms enjoy low theoretical regret, in real-world deployment they can be sensitive to individual outliers that cause the algorithm to over-correct.
A Walsh Hadamard Derived Linear Vector Symbolic Architecture
Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are `bound' together to produce a new vector in the same space.
Is Function Similarity Over-Engineered? Building a Benchmark
Binary analysis is a core component of many critical security tasks, including reverse engineering, malware analysis, and vulnerability detection.
Position: Challenges and Opportunities for Differential Privacy in the U.S. Federal Government
In this article, we seek to elucidate challenges and opportunities for differential privacy within the federal government setting, as seen by a team of differential privacy researchers, privacy lawyers, and data scientists working closely with the U. S. government.
Neural Normalized Compression Distance and the Disconnect Between Compression and Classification
It is generally well understood that predictive classification and compression are intrinsically related concepts in information theory.
Feature Selection from Differentially Private Correlations
Additionally, high-dimensional regression can leak information about individual datapoints in a dataset.
More Options for Prelabor Rupture of Membranes, A Bayesian Analysis
However, patients with prelabor rupture of membranes (PROM) have only two commonly used options for cervical ripening, Pitocin and misoprostol.
Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context
Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e. g., via byte entropy).
High-Dimensional Distributed Sparse Classification with Scalable Communication-Efficient Global Updates
As the size of datasets used in statistical learning continues to grow, distributed training of models has attracted increasing attention.
WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions
Language Models (LMs) are being proposed for mental health applications where the heightened risk of adverse outcomes means predictive performance may not be a sufficient litmus test of a model's utility in clinical practice.
Optimizing the Optimal Weighted Average: Efficient Distributed Sparse Classification
While distributed training is often viewed as a solution to optimizing linear models on increasingly large datasets, inter-machine communication costs of popular distributed approaches can dominate as data dimensionality increases.
Assemblage: Automatic Binary Dataset Construction for Machine Learning
Our results illustrate the practical need for robust corpora of high-quality Windows PE binaries in training modern learning-based binary analyses.
REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs
Automatic citation generation for sentences in a document or report is paramount for intelligence analysts, cybersecurity, news agencies, and education personnel.
SoK: A Review of Differentially Private Linear Models For High-Dimensional Data
Linear models are ubiquitous in data science, but are particularly prone to overfitting and data memorization in high dimensions.
Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges.
Comprehensive OOD Detection Improvements
As machine learning becomes increasingly prevalent in impactful decisions, recognizing when inference data is outside the model's expected input distribution is paramount for giving context to predictions.
Dimensionality Reduction
Out of Distribution (OOD) Detection
Small Effect Sizes in Malware Detection? Make Harder Train/Test Splits!
Industry practitioners care about small improvements in malware detection accuracy because their models are deployed to hundreds of millions of machines, meaning a 0. 1\% change can cause an overwhelming number of false positives.
Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations
While deep learning has enjoyed significant success in computer vision tasks over the past decade, many shortcomings still exist from a Cognitive Science (CogSci) perspective.
DDxT: Deep Generative Transformer Models for Differential Diagnosis
In the case of DDx, the proposed network has achieved a mean accuracy of 99. 82% and a mean F1 score of 0. 9472.
A Generative Approach for Image Registration of Visible-Thermal (VT) Cancer Faces
Since thermal imagery offers a unique modality to investigate pain, the U. S. National Institutes of Health (NIH) has collected a large and diverse set of cancer patient facial thermograms for AI-based pain research.
Exploring the Sharpened Cosine Similarity
Convolutional layers have long served as the primary workhorse for image classification.
cuSLINK: Single-linkage Agglomerative Clustering on the GPU
In this paper, we propose cuSLINK, a novel and state-of-the-art reformulation of the SLINK algorithm on the GPU which requires only $O(Nk)$ space and uses a parameter $k$ to trade off space and time.
Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models.
You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks
In this survey we review the current literature on attacks and their real-world occurrences, or limited evidence thereof, to critically evaluate the real-world risks of adversarial machine learning (AML) for the average entity.
Vista-Morph: Unsupervised Image Registration of Visible-Thermal Facial Pairs
For a variety of biometric cross-spectral tasks, Visible-Thermal (VT) facial pairs are used.
AVScan2Vec: Feature Learning on Antivirus Scan Data for Production-Scale Malware Corpora
Our work explores the potential of antivirus (AV) scan data as a scalable source of features for malware.
LEACE: Perfect linear concept erasure in closed form
Concept erasure aims to remove specified features from a representation.
Recasting Self-Attention with Holographic Reduced Representations
In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains.
Sparse Private LASSO Logistic Regression
LASSO regularized logistic regression is particularly useful for its built-in feature selection, allowing coefficients to be removed from deployment and producing sparse solutions.
Emergent and Predictable Memorization in Large Language Models
Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models.
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
How do large language models (LLMs) develop and evolve over the course of training?
Ranked #4 on
Language Modelling
on LAMBADA
(Perplexity metric)
The Challenge of Differentially Private Screening Rules
Linear $L_1$-regularized models have remained one of the simplest and most effective tools in data analysis, especially in information retrieval problems where n-grams over text with TF-IDF or Okapi feature values are a strong and easy baseline.
When Visible-to-Thermal Facial GAN Beats Conditional Diffusion
Thermal facial imagery offers valuable insight into physiological states such as inflammation and stress by detecting emitted radiation in the infrared spectrum, which is unseen in the visible spectra.
Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition
Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks.
A Coreset Learning Reality Check
Subsampling algorithms are a natural approach to reduce data size before fitting models on massive datasets.
BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
We find language adaptation to be effective at improving zero-shot performance in new languages.
Efficient Malware Analysis Using Metric Embeddings
In this paper, we explore the use of metric learning to embed Windows PE files in a low-dimensional vector space for downstream use in a variety of applications, including malware detection, family classification, and malware attribute tagging.
Lempel-Ziv Networks
Recurrent neural nets have been successful in processing sequences for a number of tasks; however, they are known to be both ineffective and computationally expensive when applied to very long sequences.
Crosslingual Generalization through Multitask Finetuning
We find finetuning large multilingual language models on English tasks with English prompts allows for task generalization to non-English languages that appear only in the pretraining corpus.
Ranked #1 on
Question Answering
on StoryCloze
A General Framework for Auditing Differentially Private Machine Learning
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice.
Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training
The quantification of uncertainty is important for the adoption of machine learning, especially to reject out-of-distribution (OOD) data back to human experts for review.
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
Due to the computational cost of running inference for a neural network, the need to deploy the inferential steps on a third party's compute environment or hardware is common.
Neural Bregman Divergences for Distance Learning
Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e. g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space.
Marvolo: Programmatic Data Augmentation for Practical ML-Driven Malware Detection
Data augmentation has been rare in the cyber security domain due to technical difficulties in altering data in a manner that is semantically consistent with the original data.
VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance
Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models.
A Siren Song of Open Source Reproducibility
Our argument is that this focus on code for replication is misguided if we want to improve the state of reproducible research.
Does the Market of Citations Reward Reproducible Work?
Yet to the best of our knowledge, only one work has attempted to look at this combined space, concluding that non-reproducible work is more highly cited.
Intelligent Sight and Sound: A Chronic Cancer Pain Dataset
Cancer patients experience high rates of chronic pain throughout the treatment process.
Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop at AAAI 2022
These challenges are widely studied in enterprise networks, but there are many gaps in research and practice as well as novel problems in other domains.
Out of Distribution Data Detection Using Dropout Bayesian Neural Networks
We explore the utility of information contained within a dropout based Bayesian neural network (BNN) for the task of detecting out of distribution (OOD) data.
Continuously Generalized Ordinal Regression for Linear and Deep Models
Our method, which we term continuously generalized ordinal logistic, significantly outperforms the standard ordinal logistic model over a thorough set of ordinal regression benchmark datasets.
Fooling MOSS Detection with Pretrained Language Models
In this paper we explore whether transformers can be used to solve introductory level programming assignments while bypassing commonly used AI tools to detect similarities between pieces of software.
Rank-1 Similarity Matrix Decomposition For Modeling Changes in Antivirus Consensus Through Time
Although groups of strongly correlated antivirus engines are known to exist, at present there is limited understanding of how or why these correlations came to be.
Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech
Learning to understand grounded language, which connects natural language to percepts, is a critical research area.
MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labels
Malware family classification is a significant issue with public safety and research implications that has been hindered by the high cost of expert labels.
A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels
In some problem spaces, the high cost of obtaining ground truth labels necessitates use of lower quality reference datasets.
Adversarial Transfer Attacks With Unknown Data and Class Overlap
In this work we note that as studied, current transfer attack research has an unrealistic advantage for the attacker: the attacker has the exact same training data as the victim.
Learning with Holographic Reduced Representations
HRRs today are not effective in a differentiable solution due to numerical instability, a problem we solve by introducing a projection step that forces the vectors to exist in a well behaved point in space.
Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraints
The detection of malware is a critical task for the protection of computing environments.
Evading Malware Classifiers via Monte Carlo Mutant Feature Discovery
The use of Machine Learning has become a significant part of malware detection efforts due to the influx of new malware, an ever changing threat landscape, and the ability of Machine Learning methods to discover meaningful distinctions between malicious and benign software.
Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels
These combined data are captured from similar sensors in order to bootstrap the training and transfer learning task, especially valuable because visible-thermal face datasets are limited.
Exact Acceleration of K-Means++ and K-Means$\|$
K-Means++ and its distributed variant K-Means$\|$ have become de facto tools for selecting the initial seeds of K-means.
GPU Semiring Primitives for Sparse Neighborhood Methods
High-performance primitives for mathematical operations on sparse vectors must deal with the challenges of skewed degree distributions and limits on memory consumption that are typically not issues in dense operations.
Accounting for Variance in Machine Learning Benchmarks
Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices.
Research Reproducibility as a Survival Analysis
There has been increasing concern within the machine learning community that we are in a reproducibility crisis.
Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection
Recent works within machine learning have been tackling inputs of ever-increasing size, with cybersecurity presenting sequence classification problems of particularly extreme lengths.
Sampling Approach Matters: Active Learning for Robotic Language Acquisition
Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora.
Getting Passive Aggressive About False Positives: Patching Deployed Malware Detectors
We propose a strategy for fixing false positives in production after a model has already been deployed.
The Use of AI for Thermal Emotion Recognition: A Review of Problems and Limitations in Standard Design and Data
But we also propose that thermal imagery may provide a semi-anonymous modality for computer vision, over RGB, which has been plagued by misuse in facial recognition.
Automatic Yara Rule Generation Using Biclustering
Yara rules are a ubiquitous tool among cybersecurity practitioners and analysts.
Practical Cross-modal Manifold Alignment for Grounded Language
We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world items.
COVID-19 Kaggle Literature Organization
The world has faced the devastating outbreak of Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2), or COVID-19, in 2020.
Bringing UMAP Closer to the Speed of Light with GPU Acceleration
The Uniform Manifold Approximation and Projection (UMAP) algorithm has become widely popular for its ease of use, quality of results, and support for exploratory, unsupervised, supervised, and semi-supervised learning.
Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning
Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI.
A Survey of Machine Learning Methods and Challenges for Windows Malware Classification
Malware classification is a difficult problem, to which machine learning methods have been applied for decades.
Exploratory Analysis of Covid-19 Tweets using Topic Modeling, UMAP, and DiGraphs
As the time to retweet increases, the density of connections also increase where in our sample, we found distinct users dominating the attention of Covid19 retweeters.
A New Burrows Wheeler Transform Markov Distance
Prior work inspired by compression algorithms has described how the Burrows Wheeler Transform can be used to create a distance measure for bioinformatics problems.
Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory
We treat each individual layer of the DNN as a nonlinear dynamical system and use Lyapunov theory to prove stability and robustness locally.
Would a File by Any Other Name Seem as Malicious?
Successful malware attacks on information technology systems can cause millions of dollars in damage, the exposure of sensitive and private information, and the irreversible destruction of data.
A Step Toward Quantifying Independently Reproducible Machine Learning Research
What makes a paper independently reproducible?
Heterogeneous Relational Kernel Learning
Recent work has developed Bayesian methods for the automatic statistical analysis and description of single time series as well as of homogeneous sets of time series data.
KiloGrams: Very Large N-Grams for Malware Classification
N-grams have been a common tool for information retrieval and machine learning applications for decades.
Connecting Lyapunov Control Theory to Adversarial Attacks
Significant work is being done to develop the math and tools necessary to build provable defenses, or at least bounds, against adversarial attacks of neural networks.
Barrage of Random Transforms for Adversarially Robust Defense
Defenses against adversarial examples, when using the ImageNet dataset, are historically easy to defeat.
Adversarial Attacks, Regression, and Numerical Stability Regularization
Adversarial attacks against neural networks in a regression setting are a critical yet understudied problem.
Growing and Retaining AI Talent for the United States Government
Artificial Intelligence and Machine Learning have become transformative to a number of industries, and as such many industries need for AI talent is increasing the demand for individuals with these skills.
Gradient Reversal Against Discrimination
No methods currently exist for making arbitrary neural networks fair.
Non-Negative Networks Against Adversarial Attacks
Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available.
What About Applied Fairness?
Machine learning practitioners are often ambivalent about the ethical aspects of their products.
Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Virus
As machine-learning (ML) based systems for malware detection become more prevalent, it becomes necessary to quantify the benefits compared to the more traditional anti-virus (AV) systems widely used today.
Engineering a Simplified 0-Bit Consistent Weighted Sampling
The Min-Hashing approach to sketching has become an important tool in data analysis, information retrial, and classification.
Toward Metric Indexes for Incremental Insertion and Querying
In this work we explore the use of metric index structures, which accelerate nearest neighbor queries, in the scenario where we need to interleave insertions and queries during deployment.
Fair Forests: Regularized Tree Induction to Minimize Model Bias
The potential lack of fairness in the outputs of machine learning algorithms has recently gained attention both within the research community as well as in society more broadly.
Malware Detection by Eating a Whole EXE
In this work we introduce malware detection from raw byte sequences as a fruitful research area to the larger machine learning community.
Learning the PE Header, Malware Detection with Minimal Domain Knowledge
Many efforts have been made to use various forms of domain knowledge in malware detection.
Lempel-Ziv Jaccard Distance, an Effective Alternative to Ssdeep and Sdhash
Recent work has proposed the Lempel-Ziv Jaccard Distance (LZJD) as a method to measure the similarity between binary byte sequences for malware classification.
Cryptography and Security
