Mirazul Haque
9 papers · 2020–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5) π Cross-Pollinator (11)
π
Interdisciplinary Bridge
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(21)
π₯
Unstoppable
(5)
Conferences
CVPR (3)
NAACL (2)
AAAI (1)
COLING (1)
EACL (1)
INTERSPEECH (1)
Top co-authors
Keywords
adversarial attack
(4)
large language model
(4)
prompt engineering
(2)
model efficiency
(2)
language model evaluation
(1)
automatic speech recognition
(1)
model robustness
(1)
neural network optimization
(1)
content moderation
(1)
rank correlation
(1)
backdoor attack
(1)
paraphrase generation
(1)
adversarial perturbation
(1)
copyright protection
(1)
model poisoning
(1)
computational cost
(1)
membership inference
(1)
training datum
(1)
model optimization
(1)
dynamic routing
(1)
Papers
Detecting Non-Membership in LLM Training Data via Rank Correlations
EACL 2026
Perturb Your Data: Paraphrase-Guided Training Data Watermarking
AAAI 2026
Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
NAACL 2025
HateModerate: Testing Hate Speech Detectors against Content Moderation Policies
NAACL 2024
SlothSpeech: Denial-of-service Attack Against Speech Recognition Models
INTERSPEECH 2023
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection
CVPR 2023
TestAug: A Framework for Augmenting Capability-based NLP Tests
COLING 2022
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
CVPR 2022
ILFO: Adversarial Attack on Adaptive Neural Networks
CVPR 2020