Zobrazeno 1 - 10
of 101
pro vyhledávání: '"Lohn, Andrew J"'
Autor:
Lohn, Andrew J, Jackson, Krystal Alex
We aim to demonstrate the value of mathematical models for policy debates about technological progress in cybersecurity by considering phishing, vulnerability discovery, and the dynamics between patching and exploitation. We then adjust the inputs to
Externí odkaz:
http://arxiv.org/abs/2207.13825
Adversarial patches are images designed to fool otherwise well-performing neural network-based computer vision models. Although these attacks were initially conceived of and studied digitally, in that the raw pixel values of the image were perturbed,
Externí odkaz:
http://arxiv.org/abs/2206.12725
Autor:
Lohn, Andrew J.
The resizing of images, which is typically a required part of preprocessing for computer vision systems, is vulnerable to attack. Images can be created such that the image is completely different at machine-vision scales than at other scales and the
Externí odkaz:
http://arxiv.org/abs/2010.02456
Autor:
Lohn, Andrew J.
Test, Evaluation, Verification, and Validation (TEVV) for Artificial Intelligence (AI) is a challenge that threatens to limit the economic and societal rewards that AI researchers have devoted themselves to producing. A central task of TEVV for AI is
Externí odkaz:
http://arxiv.org/abs/2009.00802
Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models. Cost-sensiti
Externí odkaz:
http://arxiv.org/abs/1910.02095
Autor:
Lohn, Andrew J.
Given that individual defenses are rarely sufficient, defense-in-depth is nearly universal and options for individual defensive layers abound. We develop a simple mathematical theory that can help in selecting the type and quantity of defenses for tw
Externí odkaz:
http://arxiv.org/abs/1910.00111
Autor:
Lohn, Andrew J.
Zero-day vulnerabilities can be accidentally or maliciously placed in code and can remain in place for years. In this study, we address an aspect of their longevity by considering the likelihood that they will be discovered in the code across version
Externí odkaz:
http://arxiv.org/abs/1808.10062
We show that, in tantalum oxide resistive memories, activation power provides a multi-level variable for information storage that can be set and read separately from the resistance. These two state variables (resistance and activation power) can be p
Externí odkaz:
http://arxiv.org/abs/1406.4033
Autor:
Lohn, Andrew J., Doyle, Barney L., Stein, Gregory J., Mickel, Patrick R., Stevens, Jim E., Marinella, Matthew J.
Publikováno v:
In Nuclear Inst. and Methods in Physics Research, B 1 August 2014 332:99-102
Autor:
Norris, Kate J., Wong, Vernon K., Onishi, Takehiro, Lohn, Andrew J., Coleman, Elane, Tompa, Gary S., Kobayashi, Nobuhiko P.
Publikováno v:
In Surface Science October 2012 606(19-20):1556-1559