Výsledky vyhledávání - "Kenneth T. Co"

Jacobian ensembles improve robustness trade-offs to adversarial attacks

Autor: Kenneth T. Co, David Martinez-Rego, Zhongyuan Hau, Emil C. Lupu

Publikováno v: Artificial Neural Networks and Machine Learning-ICANN 2022
Lecture Notes in Computer Science ISBN: 9783031159336

Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::069f3f2a91318623018a03d24d0faf1a
http://hdl.handle.net/10044/1/99620

Zobrazit plný text záznamu

Jacobian Regularization for Mitigating Universal Adversarial Perturbations

Autor: Kenneth T. Co, Emil Lupu, David Martínez-Rego

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030863791
ICANN (4)

Universal Adversarial Perturbations (UAPs) are input perturbations that can fool a neural network on large sets of data. They are a class of attacks that represents a significant threat as they facilitate realistic, practical, and low-cost attacks on

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9bc98f4f7b321f99543020f9387f3099
https://doi.org/10.1007/978-3-030-86380-7_17

Zobrazit plný text záznamu

Object Removal Attacks on LiDAR-based 3D Object Detectors

Autor: Kenneth T. Co, Emil Lupu, Zhongyuan Hau, Soteris Demetriou

Publikováno v: NDSS 2021 Workshop

LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c26166ce1131278ecf7f345581ac693

Zobrazit plný text záznamu

Procedural noise adversarial examples for black-box attacks on deep neural networks

Autor: Emil Lupu, Luis Muñoz-González, Kenneth T. Co, Sixte de Maupeou

Publikováno v: 26th ACM Conference on Computer and Communications Security
CCS

Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning algorithms at test time. Existing input-agnostic adversarial perturbati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::623f1805334de829974a98fcac2124d6
http://hdl.handle.net/10044/1/71700

Zobrazit plný text záznamu

Universal Adversarial Robustness of Texture and Shape-Biased Models

Autor: Emil Lupu, Ben Glocker, Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan

Publikováno v: IEEE International Conference on Image Processing (ICIP)

Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adversarial Perturbations (UAPs).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f56824b01ac418d469ea13216b07423

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání