Publications
Peer Reviewed Publication.
Conference Papers
-
[Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models]
Noor Islam S. Mohammad, Uluğ Bayazıt
2026 · ICML
-
[Paper Title Goes Here]
[Your Name], [Coauthor A]
[Conference Year]
-
[Paper Title Goes Here]
[Coauthor A], [Your Name]
[Conference Year]
Journal Papers
-
EdgeDetect: Adaptive Gradient Compression with Homomorphic Aggregation for Privacy-Preserving Federated Intrusion Detection
Noor Islam S. Mohammad, Mahmudul Hasan
IEEE Transactions on Information Forensics and Security (IEEE TIFS)
Under Review
-
HERALD: Harmfulness Propagation Dynamics and Layer-wise Trajectories of Adversarial Intent in Large Language Models
Noor Islam S. Mohammad, Uluğ Bayazıt
Transactions on Machine Learning Research (TMLR)
Under Review
Workshop Papers
-
HERALD: Harmfulness Propagation Dynamics and Layer-wise Trajectories of Adversarial Intent in Large Language Models
Noor Islam S. Mohammad, Uluğ Bayazıt
ICML 2026 · Statistical Frameworks for Uncertainty in Agentic Systems
-
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
Noor Islam S. Mohammad, Uluğ Bayazıt
ACL 2026 · Proceeding of 6th Workshop on Trustworthy NLP (TrustNLP)
-
Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
Noor Islam S. Mohammad, M. Hasan
ICML 2026 · Workshop on Efficient Multimodal Question Answering
-
MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions
Noor Islam S. Mohammad, T. Sheikh
ICML 2026 · 6th Muslims in Machine Learning (MusIML) Workshop
-
The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements
Noor Islam S. Mohammad, T. Sheikh
ICML 2026 · 6th Muslims in Machine Learning (MusIML) Workshop
-
Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models
Noor Islam S. Mohammad, Uluğ Bayazıt
ICML 2026 · Mechanistic Interpretability Workshop
-
CausalScene: Typed Causal Scene Graphs for Counterfactual Physical Reasoning with a Path to Video LLMs
Noor Islam S. Mohammad, Uluğ Bayazıt
CVPR 2026 · Workshop on Video Large Language Models
-
R3DC: Reliability-Guided Reveal-to-Revise Depth Completion for Cross-Domain Sparse Perception
Noor Islam S. Mohammad, Uluğ Bayazıt
CVPR 2026 · Workshop on 3D Geometry Generation for Scientific Computing
Preprints & Under Review
-
CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification
Noor Islam S. Mohammad
Research Preprint (Early Career)
-
Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning
Noor Islam S. Mohammad,Uluğ Bayazıt
Research Preprint (Early Career)
-
Data Scheduling Algorithm for Scalable and Efficient IoT Sensing in Cloud Computing
Noor Islam S. Mohammad
Research Preprint (Early Career)
-
SafeLM: A Comprehensive Framework for Safe and Trustworthy Large Language Models
Noor Islam S. Mohammad,Uluğ Bayazıt
Research Preprint (Early Career)
-
Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction
Noor Islam S. Mohammad
Research Preprint (Early Career)
-
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
Noor Islam S. Mohammad, et al.
Research Preprint (Early Career)
-
DSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation
Noor Islam S. Mohammad, Md. Muntaqim Meherab.
Research Preprint (Early Career)
-
Breaking the Temporal Complexity Barrier: Bucket Calculus for Parallel Machine Scheduling
Noor Islam S. Mohammad
Research Preprint (Early Career)