papers

Publications (131)

cs.CL2022

Fooling MOSS Detection with Pretrained Language Models

Stella Biderman, Edward Raff

As artificial intelligence (AI) technologies become increasingly powerful and prominent in society, their misuse is a growing concern. In educational settings, AI technologies coul…

cs.CR2020

Automatic Yara Rule Generation Using Biclustering

Edward Raff, Richard Zak, Gary Lopez Munoz +5

Yara rules are a ubiquitous tool among cybersecurity practitioners and analysts. Developing high-quality Yara rules to detect a malware family of interest can be labor- and time-in…

cs.CR2025

ClarAVy: A Tool for Scalable and Accurate Malware Family Labeling

Robert J. Joyce, Derek Everett, Maya Fuchs +2

Determining the family to which a malicious file belongs is an essential component of cyberattack investigation, attribution, and remediation. Performing this task manually is time…

cs.CR2024

Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection

Mohammad Mahmudul Alam, Edward Raff, Stella Biderman +2

Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges. We investigate existing long…

cs.LG2023

You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks

Edward Raff, Michel Benaroch, Andrew L. Farris

The robustness of modern machine learning (ML) models has become an increasing concern within the community. The ability to subvert a model into making errant predictions using see…

cs.LG2025

Differentially Private Iterative Screening Rules for Linear Regression

Amol Khanna, Fred Lu, Edward Raff

Linear -regularized models have remained one of the simplest and most effective tools in data science. Over the past decade, screening rules have risen in popularity as a way…

cs.LG2022

Efficient Malware Analysis Using Metric Embeddings

Ethan M. Rudd, David Krisiloff, Scott Coull +3

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…

cs.LG2026

Cybersecurity Detection Classification with Reasoning-enabled Language Models

Amol Khanna, Manu Nandan, Cristian Viorel Popa +10

The paper introduces a chain-of-thought reasoning classifier built on large language models to triage Windows endpoint security alerts, using a calibrated confidence estimator to i…

#alert triage#large language models#chain-of-thought reasoning#self-training
cs.CL2023

Emergent and Predictable Memorization in Large Language Models

Stella Biderman, USVSN Sai Prashanth, Lintang Sutawika +4

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. I…

cs.CR2024

Position: Challenges and Opportunities for Differential Privacy in the U.S. Federal Government

Amol Khanna, Adam McCormick, Andre Nguyen +2

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 researc…

cs.LG2023

Recasting Self-Attention with Holographic Reduced Representations

Mohammad Mahmudul Alam, Edward Raff, Stella Biderman +2

In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains. However, in domains with very long sequence lengths the $\mathcal{O}…

cs.LG2023

cuSLINK: Single-linkage Agglomerative Clustering on the GPU

Corey J. Nolet, Divye Gala, Alex Fender +6

In this paper, we propose cuSLINK, a novel and state-of-the-art reformulation of the SLINK algorithm on the GPU which requires only space and uses a parameter to trade…

cs.LG2024

Feature Selection from Differentially Private Correlations

Ryan Swope, Amol Khanna, Philip Doldo +2

Data scientists often seek to identify the most important features in high-dimensional datasets. This can be done through -regularized regression, but this can become ineffici…

cs.PL2025

Disassembly as Weighted Interval Scheduling with Learned Weights

Antonio Flores-Montoya, Junghee Lim, Adam Seitz +3

Disassembly is the first step of a variety of binary analysis and transformation techniques, such as reverse engineering, or binary rewriting. Recent disassembly approaches consist…

stat.ML2023

Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests

Edward Raff, James Holt

Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs, where the label is positive if and only if a po…

cs.AI2024

A Walsh Hadamard Derived Linear Vector Symbolic Architecture

Mohammad Mahmudul Alam, Alexander Oberle, Edward Raff +3

Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in are `bound' together to produce a new vector in the same…

cs.CR2022

Marvolo: Programmatic Data Augmentation for Practical ML-Driven Malware Detection

Michael D. Wong, Edward Raff, James Holt +1

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. This…

cs.LG2019

Heterogeneous Relational Kernel Learning

Andre T. Nguyen, Edward Raff

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. We exten…

cs.LG2024

Comprehensive OOD Detection Improvements

Anish Lakkapragada, Amol Khanna, Edward Raff +1

As machine learning becomes increasingly prevalent in impactful decisions, recognizing when inference data is outside the model's expected input distribution is paramount for givin…

cs.LG2023

Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile

Tyler LeBlond, Joseph Munoz, Fred Lu +4

Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecti…

cs.CV2020

The Use of AI for Thermal Emotion Recognition: A Review of Problems and Limitations in Standard Design and Data

Catherine Ordun, Edward Raff, Sanjay Purushotham

With the increased attention on thermal imagery for Covid-19 screening, the public sector may believe there are new opportunities to exploit thermal as a modality for computer visi…

eess.IV2022

Intelligent Sight and Sound: A Chronic Cancer Pain Dataset

Catherine Ordun, Alexandra N. Cha, Edward Raff +5

Cancer patients experience high rates of chronic pain throughout the treatment process. Assessing pain for this patient population is a vital component of psychological and functio…

stat.AP2024

More Options for Prelabor Rupture of Membranes, A Bayesian Analysis

Ashley Klein, Edward Raff, Elisabeth Seamon +2

An obstetric goal for a laboring mother is to achieve a vaginal delivery as it reduces the risks inherent in major abdominal surgery (i.e., a Cesarean section). Various medical int…

cs.LG2021

MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labels

Robert J. Joyce, Dev Amlani, Charles Nicholas +1

Malware family classification is a significant issue with public safety and research implications that has been hindered by the high cost of expert labels. The vast majority of cor…

cs.CL2023

BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting

Zheng-Xin Yong, Hailey Schoelkopf, Niklas Muennighoff +12

The BLOOM model is a large publicly available multilingual language model, but its pretraining was limited to 46 languages. To extend the benefits of BLOOM to other languages witho…

cs.LG2022

Continuously Generalized Ordinal Regression for Linear and Deep Models

Fred Lu, Francis Ferraro, Edward Raff

Ordinal regression is a classification task where classes have an order and prediction error increases the further the predicted class is from the true class. The standard approach…

cs.CY2023

Does Starting Deep Learning Homework Earlier Improve Grades?

Edward Raff, Cynthia Matuszek

Intuitively, students who start a homework assignment earlier and spend more time on it should receive better grades on the assignment. However, existing literature on the impact o…

cs.CV2023

A Generative Approach for Image Registration of Visible-Thermal (VT) Cancer Faces

Catherine Ordun, Alexandra Cha, Edward Raff +4

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 ther…

cs.LG2021

Bringing UMAP Closer to the Speed of Light with GPU Acceleration

Corey J. Nolet, Victor Lafargue, Edward Raff +4

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, sup…

cs.LG2018

Adversarial Attacks, Regression, and Numerical Stability Regularization

Andre T. Nguyen, Edward Raff

Adversarial attacks against neural networks in a regression setting are a critical yet understudied problem. In this work, we advance the state of the art by investigating adversar…

stat.ML2017

Malware Detection by Eating a Whole EXE

Edward Raff, Jon Barker, Jared Sylvester +3

In this work we introduce malware detection from raw byte sequences as a fruitful research area to the larger machine learning community. Building a neural network for such a probl…

cs.CL2025

Attribution in Scientific Literature: New Benchmark and Methods

Yash Saxena, Deepa Tilwani, Ali Mohammadi +4

Large language models (LLMs) present a promising yet challenging frontier for automated source citation in scientific communication. Previous approaches to citation generation have…

cs.LG2024

Neural Normalized Compression Distance and the Disconnect Between Compression and Classification

John Hurwitz, Charles Nicholas, Edward Raff

It is generally well understood that predictive classification and compression are intrinsically related concepts in information theory. Indeed, many deep learning methods are expl…

cs.CR2023

AVScan2Vec: Feature Learning on Antivirus Scan Data for Production-Scale Malware Corpora

Robert J. Joyce, Tirth Patel, Charles Nicholas +1

When investigating a malicious file, searching for related files is a common task that malware analysts must perform. Given that production malware corpora may contain over a billi…

cs.LG2026

Bayesian Meta-Analyses Could Be More: A Case Study in Trial of Labor After a Cesarean-section Outcomes and Complications

Ashley Klein, Edward Raff, Marcia DesJardin

The meta-analysis's utility is dependent on previous studies having accurately captured the variables of interest, but in medical studies, a key decision variable that impacts a ph…

cs.LG2023

A General Framework for Auditing Differentially Private Machine Learning

Fred Lu, Joseph Munoz, Maya Fuchs +5

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward…

cs.CR2023

Semi-supervised Classification of Malware Families Under Extreme Class Imbalance via Hierarchical Non-Negative Matrix Factorization with Automatic Model Selection

Maksim E. Eren, Manish Bhattarai, Robert J. Joyce +3

Identification of the family to which a malware specimen belongs is essential in understanding the behavior of the malware and developing mitigation strategies. Solutions proposed…

cs.CR2018

Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Virus

William Fleshman, Edward Raff, Richard Zak +2

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) s…

stat.ML2017

Fair Forests: Regularized Tree Induction to Minimize Model Bias

Edward Raff, Jared Sylvester, Steven Mills

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. Su…

cs.AI2024

WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions

Seyedali Mohammadi, Edward Raff, Jinendra Malekar +3

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 te…

cs.CR2026

Large Byte Model: Teaching Language Models About Compiled Code

Florian Störtz, Catalin-Andrei Stan, Alexandru Dinu +4

Malware analysis starts with the raw bytes of an executable program, and tools to "lift" these to higher-level representations, such as assembly, are expensive and subject to error…

cs.IR2020

COVID-19 Kaggle Literature Organization

Maksim Ekin Eren, Nick Solovyev, Edward Raff +2

The world has faced the devastating outbreak of Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2), or COVID-19, in 2020. Research in the subject matter was fast-tracked…

cs.CR2026

Cybersecurity is the True Frontier for Generative AI Success or Failure

Edward Raff, Maor Ashkenazi, Sagar Samtani +2

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate proce…

cs.CV2023

When Visible-to-Thermal Facial GAN Beats Conditional Diffusion

Catherine Ordun, Edward Raff, Sanjay Purushotham

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…

cs.LG2025

A Vector Symbolic Approach to Multiple Instance Learning

Ehsan Ahmed Dhrubo, Mohammad Mahmudul Alam, Edward Raff +2

Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff cons…

cs.CV2022

VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

Katherine Crowson, Stella Biderman, Daniel Kornis +4

Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel method…

cs.LG2026

Adversarial Samples Are Not Created Equal

Jennifer Crawford, Amol Khanna, Fred Lu +4

Over the past decade, numerous theories have been proposed to explain the widespread vulnerability of deep neural networks to adversarial evasion attacks. Among these, the theory o…

cs.CR2022

Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop at AAAI 2022

James Holt, Edward Raff, Ahmad Ridley +7

The workshop will focus on the application of AI to problems in cyber security. Cyber systems generate large volumes of data, utilizing this effectively is beyond human capabilitie…

cs.LG2019

Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory

Arash Rahnama, Andre T. Nguyen, Edward Raff

Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the D…

stat.ML2019

Non-Negative Networks Against Adversarial Attacks

William Fleshman, Edward Raff, Jared Sylvester +2

Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available. We make progress toward this probl…

cs.CV2026

Learning to Segment using Summary Statistics and Weak Supervision

Omkar Kulkarni, Edward Raff, Tim Oates

Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models to alleviate this burden, b…

cs.CL2024

Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context

Nilanjana Das, Edward Raff, Manas Gaur

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily…

cs.LG2026

ML-Powered LDAP Reconnaissance Detection using Weak Supervision

Shaefer Drew, Edward Raff, Michael Brautbar +6

Lightweight Directory Access Protocol (LDAP) is a protocol that allows users to query and modify Active Directory (AD) data. By default, all users have read access to all AD data t…

cs.LG2025

LEACE: Perfect linear concept erasure in closed form

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel +3

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. rem…

cs.LG2024

Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling

Skyler Wu, Fred Lu, Edward Raff +1

Online learning methods, like the seminal Passive-Aggressive (PA) classifier, are still highly effective for high-dimensional streaming data, out-of-core processing, and other thro…

cs.CR2026

ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage

Chang Liu, Noah Fleischmann, Nicolò Altamura +3

Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis, or CVE labels for single-buil…

cs.SE2026

Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks

Seyedreza Mohseni, Sarvesh Baskar, Edward Raff +1

Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice, this often requires days or even months of manual…

cs.CR2021

Rank-1 Similarity Matrix Decomposition For Modeling Changes in Antivirus Consensus Through Time

Robert J. Joyce, Edward Raff, Charles Nicholas

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. Using a corpus o…

cs.LG2022

A Siren Song of Open Source Reproducibility

Edward Raff, Andrew L. Farris

As reproducibility becomes a greater concern, conferences have largely converged to a strategy of asking reviewers to indicate whether code was attached to a submission. This is pa…

cs.LG2020

Getting Passive Aggressive About False Positives: Patching Deployed Malware Detectors

Edward Raff, Bobby Filar, James Holt

False positives (FPs) have been an issue of extreme importance for anti-virus (AV) systems for decades. As more security vendors turn to machine learning, alert deluge has hit crit…

cs.DS2025

Intermediate N-Gramming: Deterministic and Fast N-Grams For Large N and Large Datasets

Ryan R. Curtin, Fred Lu, Edward Raff +1

The number of n-gram features grows exponentially in n, making it computationally demanding to compute the most frequent n-grams even for n as small as 3. Motivated by our producti…

stat.ML2018

Engineering a Simplified 0-Bit Consistent Weighted Sampling

Edward Raff, Jared Sylvester, Charles Nicholas

The Min-Hashing approach to sketching has become an important tool in data analysis, information retrial, and classification. To apply it to real-valued datasets, the ICWS algorith…

cs.LG2023

Sparse Private LASSO Logistic Regression

Amol Khanna, Fred Lu, Edward Raff +1

LASSO regularized logistic regression is particularly useful for its built-in feature selection, allowing coefficients to be removed from deployment and producing sparse solutions.…

stat.ML2018

Gradient Reversal Against Discrimination

Edward Raff, Jared Sylvester

No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used…

cs.RO2020

Sampling Approach Matters: Active Learning for Robotic Language Acquisition

Nisha Pillai, Edward Raff, Francis Ferraro +1

Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning ap…

cs.RO2020

Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning

Patrick Jenkins, Rishabh Sachdeva, Gaoussou Youssouf Kebe +7

Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI. In practice the da…

cs.CR2026

SubstratumGraphEnv: Reinforcement Learning Environment (RLE) for Modeling System Attack Paths

Bahirah Adewunmi, Edward Raff, Sanjay Purushotham

Automating network security analysis, particularly the identification of potential attack paths, presents significant challenges. Due in part to the sequential, interconnected, and…

cs.LG2025

Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack

Edward Raff, Karen Kukla, Michel Benaroch +1

Bad actors, primarily distressed firms, have the incentive and desire to manipulate their financial reports to hide their distress and derive personal gains. As attackers, these fi…

cs.LG2024

High-Dimensional Distributed Sparse Classification with Scalable Communication-Efficient Global Updates

Fred Lu, Ryan R. Curtin, Edward Raff +2

As the size of datasets used in statistical learning continues to grow, distributed training of models has attracted increasing attention. These methods partition the data and expl…

cs.LG2024

Optimizing the Optimal Weighted Average: Efficient Distributed Sparse Classification

Fred Lu, Ryan R. Curtin, Edward Raff +2

While distributed training is often viewed as a solution to optimizing linear models on increasingly large datasets, inter-machine communication costs of popular distributed approa…

cs.LG2023

The Challenge of Differentially Private Screening Rules

Amol Khanna, Fred Lu, Edward Raff

Linear -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 wi…

cs.AI2021

Learning with Holographic Reduced Representations

Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi +4

Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors by associating each vector with an abstract concept, and providing m…

cs.CR2019

Would a File by Any Other Name Seem as Malicious?

Andre T. Nguyen, Edward Raff, Aaron Sant-Miller

Successful malware attacks on information technology systems can cause millions of dollars in damage, the exposure of sensitive and private information, and the irreversible destru…

cs.CL2023

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Stella Biderman, Hailey Schoelkopf, Quentin Anthony +10

How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce \textit{Py…

cs.LG2023

A Coreset Learning Reality Check

Fred Lu, Edward Raff, James Holt

Subsampling algorithms are a natural approach to reduce data size before fitting models on massive datasets. In recent years, several works have proposed methods for subsampling ro…

cs.LG2023

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition

Luke E. Richards, Edward Raff, Cynthia Matuszek

Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks. An understudied question in that community is: for whom do the…

cs.LG2023

Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations

Edward Raff, Amol Khanna, Fred Lu

To the best of our knowledge, there are no methods today for training differentially private regression models on sparse input data. To remedy this, we adapt the Frank-Wolfe algori…

cs.CL2026

Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions

Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba +4

Do LLMs genuinely incorporate external definitions, or do they primarily rely on their parametric knowledge? To address these questions, we conduct controlled experiments across mu…

cs.CR2018

Lempel-Ziv Jaccard Distance, an Effective Alternative to Ssdeep and Sdhash

Edward Raff, Charles K. Nicholas

Recent work has proposed the Lempel-Ziv Jaccard Distance (LZJD) as a method to measure the similarity between binary byte sequences for malware classification. We propose and test…

cs.LG2026

Towards Improved Anomaly Detection for Cloud Cybersecurity via Graph Neural Networks

Manu Nandan, TJ Jaymes, Michael Brautbar +1

Detecting security threats in an organization's cloud computing environment has become necessary due to the increased reliance on cloud infrastructure. Logging of all cloud computi…

cs.CR2023

MalDICT: Benchmark Datasets on Malware Behaviors, Platforms, Exploitation, and Packers

Robert J. Joyce, Edward Raff, Charles Nicholas +1

Existing research on malware classification focuses almost exclusively on two tasks: distinguishing between malicious and benign files and classifying malware by family. However, m…

cs.DS2018

Toward Metric Indexes for Incremental Insertion and Querying

Edward Raff, Charles Nicholas

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 dep…

cs.CL2023

Crosslingual Generalization through Multitask Finetuning

Niklas Muennighoff, Thomas Wang, Lintang Sutawika +16

Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting, but so far explorations of MTF have focused on Engl…

cs.DL2022

Does the Market of Citations Reward Reproducible Work?

Edward Raff

The field of bibliometrics, studying citations and behavior, is critical to the discussion of reproducibility. Citations are one of the primary incentive and reward systems for aca…

cs.LG2024

Is Function Similarity Over-Engineered? Building a Benchmark

Rebecca Saul, Chang Liu, Noah Fleischmann +4

Binary analysis is a core component of many critical security tasks, including reverse engineering, malware analysis, and vulnerability detection. Manual analysis is often time-con…

cs.LG2023

Small Effect Sizes in Malware Detection? Make Harder Train/Test Splits!

Tirth Patel, Fred Lu, Edward Raff +3

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…

cs.CL2021

Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech

Gaoussou Youssouf Kebe, Luke E. Richards, Edward Raff +2

Learning to understand grounded language, which connects natural language to percepts, is a critical research area. Prior work in grounded language acquisition has focused primaril…

cs.CV2025

Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent

Philip Doldo, Derek Everett, Amol Khanna +2

Projected Gradient Descent (PGD) under the ball has become one of the defacto methods used in adversarial robustness evaluation for computer vision (CV) due to its relia…

cs.LG2022

Lempel-Ziv Networks

Rebecca Saul, Mohammad Mahmudul Alam, John Hurwitz +3

Sequence processing has long been a central area of machine learning research. Recurrent neural nets have been successful in processing sequences for a number of tasks; however, th…

cs.LG2021

A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels

Robert J. Joyce, Edward Raff, Charles Nicholas

In some problem spaces, the high cost of obtaining ground truth labels necessitates use of lower quality reference datasets. It is difficult to benchmark model performance using th…

cs.CR2026

Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes

Derek Everett, Edward Raff, James Holt

Malware poses a critical and ever-evolving threat, and robust and effective systems for detecting and classifying malware are of essential importance. -grams features are among…

cs.LG2022

Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training

Derek Everett, Andre T. Nguyen, Luke E. Richards +1

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. Yet progr…

cs.LG2022

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations

Mohammad Mahmudul Alam, Edward Raff, Tim Oates +1

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. If t…

cs.LG2021

Accounting for Variance in Machine Learning Benchmarks

Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi +14

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 variati…

stat.CO2023

An Easy Rejection Sampling Baseline via Gradient Refined Proposals

Edward Raff, Mark McLean, James Holt

Rejection sampling is a common tool for low dimensional problems (), often touted as an "easy" way to obtain valid samples from a distribution of interest. In…

cs.CR2025

Zipf-Gramming: Scaling Byte N-Grams Up to Production Sized Malware Corpora

Edward Raff, Ryan R. Curtin, Derek Everett +2

A classifier using byte n-grams as features is the only approach we have found fast enough to meet requirements in size (sub 2 MB), speed (multiple GB/s), and latency (sub 10 ms) f…

cs.CR2024

Living off the Analyst: Harvesting Features from Yara Rules for Malware Detection

Siddhant Gupta, Fred Lu, Andrew Barlow +5

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 acto…

cs.CV2021

Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels

Catherine Ordun, Edward Raff, Sanjay Purushotham

Thermal images reveal medically important physiological information about human stress, signs of inflammation, and emotional mood that cannot be seen on visible images. Providing a…

cs.CR2025

Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation

Seyedreza Mohseni, Seyedali Mohammadi, Deepa Tilwani +5

Malware authors often employ code obfuscations to make their malware harder to detect. Existing tools for generating obfuscated code often require access to the original source cod…

cs.LG2021

Adversarial Transfer Attacks With Unknown Data and Class Overlap

Luke E. Richards, André Nguyen, Ryan Capps +3

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. Th…