Zayd Hammoudeh
5 papers · 2020–2024 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(16)
🏆
Keyword Champion
Venues
Top co-authors
Research topics
Machine Learning
(4)
Deep Learning
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Artificial Intelligence
(2)
Natural Language Processing
(2)
Applications · Natural Language Processing
(2)
Core AI
(2)
Core Methods
(2)
Computer Science
(1)
Security & Privacy
(1)
Application Areas
(1)
Applications · Computer Science
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
backdoor attack
(2)
poisoning attack
(2)
natural language processing
(1)
text classification
(1)
sentiment classification
(1)
adversarial training
(1)
model interpretability
(1)
adversarial attack
(1)
latent representation
(1)
randomized smoothing
(1)
binary classifier
(1)
domain shift
(1)
positive-unlabeled learning
(1)
unlabeled data
(1)
certified defense
(1)
adversarial text
(1)
influence estimation
(1)
gradient boosted decision tree
(1)
perturbation detection
(1)
large language model
(1)
Papers
Provable Robustness against a Union of L_0 Adversarial Attacks
AAAI 2024
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
JMLR 2023
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
EMNLP 2023
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations
EMNLP 2021
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
NeurIPS 2020