Следене
Neal Mangaokar
Neal Mangaokar
Потвърден имейл адрес: umich.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
A Azizi, I Tahmid, A Waheed, N Mangaokar, J Pu, M Javed, CK Reddy, ...
30th USENIX Security Symposium (USENIX Security 2021), 2021
702021
Deepfake Videos in the Wild: Analysis and Detection
J Pu (co-lead), N Mangaokar (co-lead), L Kelly, P Bhattacharya, ...
28th ACM World Wide Web Conference (WWW 2021), 2021
42*2021
Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
N Mangaokar, J Pu, P Bhattacharya, CK Reddy, B Viswanath
5th IEEE European Symposium on Security and Privacy (EuroS&P 2020), 139-157, 2020
272020
NoiseScope: Detecting Deepfake Images in a Blind Setting
J Pu, N Mangaokar, B Wang, C K. Reddy, B Viswanath
36th ACM Annual Computer Security Applications Conference (ACSAC 2020), 2020
252020
Graphite: Generating automatic physical examples for machine-learning attacks on computer vision systems
R Feng, N Mangaokar, J Chen, E Fernandes, S Jha, A Prakash
2022 IEEE 7th European symposium on security and privacy (EuroS&P), 664-683, 2022
102022
Dispelling misconceptions and characterizing the failings of deepfake detection
N Mangaokar, A Prakash
IEEE Security & Privacy 20 (2), 61-67, 2021
82021
Towards Adversarially Robust Deepfake Detection: An Ensemble Approach
A Hooda (co-lead), N Mangaokar (co-lead), R Feng, K Fawaz, S Jha, ...
arXiv preprint arXiv:2202.05687, 2022
5*2022
Investigating Stateful Defenses Against Black-Box Adversarial Examples
R Feng (co-lead), A Hooda (co-lead), N Mangaokar (co-lead), K Fawaz, ...
arXiv preprint arXiv:2303.06280, 2023
32023
D4: Detection of adversarial diffusion deepfakes using disjoint ensembles
A Hooda, N Mangaokar, R Feng, K Fawaz, S Jha, A Prakash
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
22024
Stateful defenses for machine learning models are not yet secure against black-box attacks
R Feng, A Hooda, N Mangaokar, K Fawaz, S Jha, A Prakash
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications …, 2023
22023
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
N Mangaokar, A Hooda, J Choi, S Chandrashekaran, K Fawaz, S Jha, ...
arXiv preprint arXiv:2402.15911, 2024
12024
Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks
A Hooda (co-lead), N Mangaokar (co-lead), R Feng, K Fawaz, S Jha, ...
AdvML Frontiers Workshop at 40th International Conference on Machine …, 0
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–12