Следене
Zayd Hammoudeh, Ph.D.
Zayd Hammoudeh, Ph.D.
Qualtrics AI
Потвърден имейл адрес: qualtrics.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
Fast sampling of perfectly uniform satisfying assignments
D Achlioptas, ZS Hammoudeh, P Theodoropoulos
International Conference on Theory and Applications of Satisfiability …, 2018
432018
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
Z Hammoudeh, D Lowd
Advances in Neural Information Processing Systems 33 (NeurIPS'20), 2020
282020
Training Data Influence Analysis and Estimation: A Survey
Z Hammoudeh, D Lowd
arXiv preprint arXiv:2212.04612, 2022
272022
Identifying a training-set attack's target using renormalized influence estimation
Z Hammoudeh, D Lowd
Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications …, 2022
192022
Fast and flexible probabilistic model counting
D Achlioptas, Z Hammoudeh, P Theodoropoulos
International Conference on Theory and Applications of Satisfiability …, 2018
152018
Adapting and evaluating influence-estimation methods for gradient-boosted decision trees
J Brophy, Z Hammoudeh, D Lowd
Journal of Machine Learning Research 24 (154), 1-48, 2023
142023
Clustering-based, fully automated mixed-bag jigsaw puzzle solving
Z Hammoudeh, C Pollett
Computer Analysis of Images and Patterns: 17th International Conference …, 2017
9*2017
Reducing Certified Regression to Certified Classification for General Poisoning Attacks
Z Hammoudeh, D Lowd
1st IEEE Conference on Secure and Trustworthy Machine Learning (SaTML'23), 2023
72023
Large language models are better adversaries: Exploring generative clean-label backdoor attacks against text classifiers
W You, Z Hammoudeh, D Lowd
arXiv preprint arXiv:2310.18603, 2023
52023
Simple, Attack-Agnostic Defense Against Targeted Training Set Attacks Using Cosine Similarity
Z Hammoudeh, D Lowd
ICML'21 Workshop on Uncertainty & Robustness in Deep Learning (UDL), 2021
52021
Provable Robustness Against a Union of Adversarial Attacks
Z Hammoudeh, D Lowd
arXiv preprint arXiv:2302.11628, 2023
3*2023
Make deep learning great again: character-level RNN speech generation in the style of Donald Trump
B Sherman, Z Hammoudeh
32017
On the practicality of learning models for network telemetry
J Soheil, Z Hammoudeh, R Durairajan, D Lowd, R Rejaie, W Willinger
Proceedings of Network Traffic Measurement and Analysis Conference, 2020
22020
Certified and Forensic Defenses against Poisoning and Backdoor Attacks
Z Hammoudeh
University of Oregon, 2024
2024
Provable Robustness against a Union of L_0 Adversarial Attacks
Z Hammoudeh, D Lowd
Proceedings of the AAAI Conference on Artificial Intelligence 38 (19), 21134 …, 2024
2024
Training Set Influence Analysis and Estimation
Z Hammoudeh
2022
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations
Z Xie, J Brophy, A Noack, W You, K Asthana, C Perkins, SA Reis, ...
Proceedings of the Fourth Blackbox NLP Workshop on Analyzing and …, 2021
2021
Positive-Unlabeled Learning with Arbitrarily Non-Representative Labeled Data
Z Hammoudeh, D Lowd
ICML'20 Workshop on Uncertainty & Robustness in Deep Learning (UDL), 2020
2020
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–18