Alvi Md Ishmam
5 papers · 2024–2026 · 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 · Bronze
🗺️
Taxonomy Completionist
(15)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
vision-language model
(2)
natural language inference
(1)
claim verification
(1)
multimodal learning
(1)
fine-grained classification
(1)
fine-grained detection
(1)
bilevel optimization
(1)
backdoor attack
(1)
adversarial attack
(1)
black-box attack
(1)
poisoning attack
(1)
foundation model
(1)
multimodal document
(1)
harmful fine-tuning
(1)
multimodal reasoning
(1)
cross-modal attention
(1)
evidence extraction
(1)
universal adversarial perturbation
(1)
knowledge alignment
(1)
multimodal foundation model
(1)
Papers
Immunizing Models Against Harmful Long-Horizon Fine-Tuning via Contractive Optimization Dynamics
CVPR 2026
LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models
AAAI 2026
SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models
ACL 2026
M3D: MultiModal MultiDocument Fine-Grained Inconsistency Detection
EMNLP 2024
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
CVPR 2024