4 citations · 13 across the 19 of their papers we have counts for
20 papers
AIRRI: Towards a Human-Readable, Machine-Resistant Reading Interface
Emory Salaun, Syed Ayon, Kaleel Mahmood +1
The rapid advancement of image-to-text extraction systems and large language models (LLMs) poses new challenges for educational assessment by making assignment materials easy to tr…
Analyzing Physical Adversarial Example Threats to Machine Learning in Election Systems
Khaleque Md Aashiq Kamal, Surya Eada, Aayushi Verma +4
Developments in the machine learning voting domain have shown both promising results and risks. Trained models perform well on ballot classification tasks (> 99% accuracy) but are…
On the Evidentiary Limits of Membership Inference for Copyright Auditing
Murat Bilgehan Ertan, Emirhan Böge, Min Chen +2
As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used duri…
EMTSF:Extraordinary Mixture of SOTA Models for Time Series Forecasting
Musleh Alharthi, Kaleel Mahmood, Sarosh Patel +1
The immense success of the Transformer architecture in Natural Language Processing has led to its adoption in Time Se ries Forecasting (TSF), where superior performance has been sh…
Busting the Paper Ballot: Voting Meets Adversarial Machine Learning
Kaleel Mahmood, Caleb Manicke, Ethan Rathbun +5
We show the security risk associated with using machine learning classifiers in United States election tabulators. The central classification task in election tabulation is decidin…
Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Tasks
Murat Bilgehan Ertan, Ronak Sahu, Phuong Ha Nguyen +2
We introduce ROAR (Robust Object Removal and Re-annotation), a scalable framework for privacy-preserving dataset obfuscation that eliminates sensitive objects instead of modifying…
Efficient Context Propagating Perceiver Architectures for Auto-Regressive Language Modeling
Kaleel Mahmood, Shaoyi Huang
One of the key challenges in Transformer architectures is the quadratic complexity of the attention mechanism, which limits the efficient processing of long sequences. Many recent…
Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack
Nicole Meng, Caleb Manicke, David Chen +4
Adversarial examples represent a serious issue for the application of machine learning models in many sensitive domains. For generating adversarial examples, decision based black-b…
Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
Jieren Deng, Hanbin Hong, Aaron Palmer +5
Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achievi…
Distilling Adversarial Robustness Using Heterogeneous Teachers
Jieren Deng, Aaron Palmer, Rigel Mahmood +4
Achieving resiliency against adversarial attacks is necessary prior to deploying neural network classifiers in domains where misclassification incurs substantial costs, e.g., self-…
AutoReP: Automatic ReLU Replacement for Fast Private Network Inference
Hongwu Peng, Shaoyi Huang, Tong Zhou +11
The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues. Private inference (PI) techniques using cryptographic prim…
Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
Lijun Zhang, Xiao Liu, Kaleel Mahmood +2
Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison…
Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration
Shaoyi Huang, Haowen Fang, Kaleel Mahmood +7
Biologically inspired Spiking Neural Networks (SNNs) have attracted significant attention for their ability to provide extremely energy-efficient machine intelligence through event…
Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning
Ethan Rathbun, Kaleel Mahmood, Sohaib Ahmad +2
Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized t…
Privacy Attacks Against Biometric Models with Fewer Samples: Incorporating the Output of Multiple Models
Sohaib Ahmad, Benjamin Fuller, Kaleel Mahmood
Authentication systems are vulnerable to model inversion attacks where an adversary is able to approximate the inverse of a target machine learning model. Biometric models are a pr…
Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
Nuo Xu, Kaleel Mahmood, Haowen Fang +3
Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and recent advances in classification performance. However, unlike traditional deep le…
Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks
Kaleel Mahmood, Rigel Mahmood, Ethan Rathbun +1
The field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be…
On the Robustness of Vision Transformers to Adversarial Examples
Kaleel Mahmood, Rigel Mahmood, Marten van Dijk
Recent advances in attention-based networks have shown that Vision Transformers can achieve state-of-the-art or near state-of-the-art results on many image classification tasks. Th…
Beware the Black-Box: on the Robustness of Recent Defenses to Adversarial Examples
Kaleel Mahmood, Deniz Gurevin, Marten van Dijk +1
Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine…
BUZz: BUffer Zones for defending adversarial examples in image classification
Kaleel Mahmood, Phuong Ha Nguyen, Lam M. Nguyen +2
We propose a novel defense against all existing gradient based adversarial attacks on deep neural networks for image classification problems. Our defense is based on a combination…