491 citations · 652 across the 15 of their papers we have counts for
16 papers
Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
Kevin Eykholt, Farhan Ahmed, Pratik Vaishnavi +1
The vulnerability of machine learning models in adversarial scenarios has garnered significant interest in the academic community over the past decade, resulting in a myriad of att…
URET: Universal Robustness Evaluation Toolkit (for Evasion)
Kevin Eykholt, Taesung Lee, Douglas Schales +3
Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical i…
Accelerating Certified Robustness Training via Knowledge Transfer
Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati
Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Alth…
Ares: A System-Oriented Wargame Framework for Adversarial ML
Farhan Ahmed, Pratik Vaishnavi, Kevin Eykholt +1
Since the discovery of adversarial attacks against machine learning models nearly a decade ago, research on adversarial machine learning has rapidly evolved into an eternal war bet…
Transferring Adversarial Robustness Through Robust Representation Matching
Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati
With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks again…
Separation of Powers in Federated Learning
Pau-Chen Cheng, Kevin Eykholt, Zhongshu Gu +4
Federated Learning (FL) enables collaborative training among mutually distrusting parties. Model updates, rather than training data, are concentrated and fused in a central aggrega…
Adaptive Verifiable Training Using Pairwise Class Similarity
Shiqi Wang, Kevin Eykholt, Taesung Lee +2
Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion…
Can Attention Masks Improve Adversarial Robustness?
Pratik Vaishnavi, Tianji Cong, Kevin Eykholt +2
Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear n…
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders
Pratik Vaishnavi, Kevin Eykholt, Atul Prakash +1
Adversarial machine learning is a well-studied field of research where an adversary causes predictable errors in a machine learning algorithm through precise manipulation of the in…
Robust Classification using Robust Feature Augmentation
Kevin Eykholt, Swati Gupta, Atul Prakash +3
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible…
Designing Adversarially Resilient Classifiers using Resilient Feature Engineering
Kevin Eykholt, Atul Prakash
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlate…
Physical Adversarial Examples for Object Detectors
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
Deep neural networks (DNNs) are vulnerable to adversarial examples-maliciously crafted inputs that cause DNNs to make incorrect predictions. Recent work has shown that these attack…
Tyche: Risk-Based Permissions for Smart Home Platforms
Amir Rahmati, Earlence Fernandes, Kevin Eykholt +1
Emerging smart home platforms, which interface with a variety of physical devices and support third-party application development, currently use permission models inspired by smart…
Note on Attacking Object Detectors with Adversarial Stickers
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable…
Robust Physical-World Attacks on Deep Learning Models
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes +6
Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. G…
Internet of Things Security Research: A Rehash of Old Ideas or New Intellectual Challenges?
Earlence Fernandes, Amir Rahmati, Kevin Eykholt +1
The Internet of Things (IoT) is a new computing paradigm that spans wearable devices, homes, hospitals, cities, transportation, and critical infrastructure. Building security into…