Volgen
Kevin Eykholt
Kevin Eykholt
Geverifieerd e-mailadres voor ibm.com
Titel
Geciteerd door
Geciteerd door
Jaar
Robust physical-world attacks on deep learning visual classification
K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, C Xiao, A Prakash, ...
Proceedings of the IEEE conference on computer vision and pattern …, 2018
2870*2018
Physical adversarial examples for object detectors
D Song, K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, F Tramer, ...
12th USENIX workshop on offensive technologies (WOOT 18), 2018
4782018
Internet of things security research: A rehash of old ideas or new intellectual challenges?
E Fernandes, A Rahmati, K Eykholt, A Prakash
IEEE Security & Privacy 15 (4), 79-84, 2017
1292017
Note on attacking object detectors with adversarial stickers
K Eykholt, I Evtimov, E Fernandes, B Li, D Song, T Kohno, A Rahmati, ...
arXiv preprint arXiv:1712.08062, 2017
422017
Tyche: A risk-based permission model for smart homes
A Rahmati, E Fernandes, K Eykholt, A Prakash
2018 IEEE Cybersecurity Development (SecDev), 29-36, 2018
362018
Robust physical-world attacks on deep learning models (2017)
K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, C Xiao, A Prakash, ...
arXiv preprint arXiv:1707.08945, 2018
202018
Robust physical-world attacks on deep learning visual classification
K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, C Xiao, A Prakash, ...
192020
Tyche: Risk-based permissions for smart home platforms
A Rahmati, E Fernandes, K Eykholt, A Prakash
arXiv preprint arXiv:1801.04609, 2018
122018
Separation of powers in federated learning (poster paper)
PC Cheng, K Eykholt, Z Gu, H Jamjoom, KR Jayaram, E Valdez, A Verma
Proceedings of the First Workshop on Systems Challenges in Reliable and …, 2021
82021
Can attention masks improve adversarial robustness?
P Vaishnavi, T Cong, K Eykholt, A Prakash, A Rahmati
International Workshop on Engineering Dependable and Secure Machine Learning …, 2020
82020
Transferring adversarial robustness through robust representation matching
P Vaishnavi, K Eykholt, A Rahmati
31st USENIX Security Symposium (USENIX Security 22), 2083-2098, 2022
72022
Heimdall: A privacy-respecting implicit preference collection framework
A Rahmati, E Fernandes, K Eykholt, X Chen, A Prakash
Proceedings of the 15th Annual International Conference on Mobile Systems …, 2017
72017
Ares: A system-oriented wargame framework for adversarial ML
F Ahmed, P Vaishnavi, K Eykholt, A Rahmati
2022 IEEE Security and Privacy Workshops (SPW), 73-79, 2022
52022
Ensuring Authorized Updates in Multi-user {Database-Backed} Applications
K Eykholt, A Prakash, B Mozafari
26th USENIX Security Symposium (USENIX Security 17), 1445-1462, 2017
42017
Accelerating certified robustness training via knowledge transfer
P Vaishnavi, K Eykholt, A Rahmati
Advances in Neural Information Processing Systems 35, 5269-5281, 2022
32022
Adaptive verifiable training using pairwise class similarity
S Wang, K Eykholt, T Lee, J Jang, I Molloy
Proceedings of the AAAI Conference on Artificial Intelligence 35 (11), 10201 …, 2021
32021
Designing adversarially resilient classifiers using resilient feature engineering
K Eykholt, A Prakash
arXiv preprint arXiv:1812.06626, 2018
32018
Constraining neural networks for robustness through alternative encoding
K Eykholt, T Lee, IM Molloy, J Jang
US Patent 11,847,555, 2023
22023
{URET}: Universal Robustness Evaluation Toolkit (for Evasion)
K Eykholt, T Lee, D Schales, J Jang, I Molloy
32nd USENIX Security Symposium (USENIX Security 23), 3817-3833, 2023
22023
Robust classification using robust feature augmentation
K Eykholt, S Gupta, A Prakash, A Rahmati, P Vaishnavi, H Zheng
arXiv preprint arXiv:1905.10904, 2019
22019
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20