Spremljaj
Pedram Zaree
Naslov
Navedeno
Navedeno
Leto
Survey of vulnerabilities in large language models revealed by adversarial attacks
E Shayegani, MAA Mamun, Y Fu, P Zaree, Y Dong, N Abu-Ghazaleh
arXiv preprint arXiv:2310.10844, 2023
1462023
That Doesn't Go There: Attacks on Shared State in {Multi-User} Augmented Reality Applications
C Slocum, Y Zhang, E Shayegani, P Zaree, N Abu-Ghazaleh, J Chen
33rd USENIX Security Symposium (USENIX Security 24), 2761-2778, 2024
102024
Survey of vulnerabilities in large language models revealed by adversarial attacks, 2023
E Shayegani, MAA Mamun, Y Fu, P Zaree, Y Dong, N Abu-Ghazaleh
URL https://arxiv. org/abs/2310.10844, 0
5
Deepmem: Ml models as storage channels and their (mis-) applications
MA Al Mamun, QM Alam, E Shaigani, P Zaree, I Alouani, N Abu-Ghazaleh
arXiv preprint arXiv:2307.08811, 2023
32023
Vulnerabilities of Large Language Models to Adversarial Attacks
Y Fu, E Shayegan, MM Al Abdullah, P Zaree, N Abu-Ghazaleh, Y Dong
Proceedings of the 62nd Annual Meeting of the Association for Computational …, 2024
12024
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
P Zaree, MAA Mamun, QM Alam, Y Dong, I Alouani, N Abu-Ghazaleh
arXiv preprint arXiv:2502.15334, 2025
2025
Securing Shared State in Multi-User Augmented Reality
J Chen, C Slocum, Y Zhang, E Shayegani, P Zaree, N Abu-Ghazaleh
2024 IEEE International Symposium on Mixed and Augmented Reality Adjunct …, 2024
2024
Co (ve) rtex: ML Models as storage channels and their (mis-) applications
MAA Mamun, QM Alam, E Shayegani, P Zaree, I Alouani, ...
arXiv preprint arXiv:2307.08811, 2023
2023
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–8