AIConfPaper
← Search

Zaber Ibn Abdul Hakim

4 accepted papers

2026

Immunizing Models Against Harmful Long-Horizon Fine-Tuning via Contractive Optimization Dynamics

Najibul Haque Sarker, Zaber Ibn Abdul Hakim, Ali Asgarov, Chia-Wei Tang, Alvi Md Ishmam, Chris Thomas
CVPR 2026

Fine-tuning has become the default way to adapt powerful foundation models, but this also enables low-cost repurposing for harmful objectives. Existing immunization methods try to optimize local geometry or simulate short attacker horizons, and penalize observed loss drops. However, in practice, dow

Cited by 0Source ↗Scholar ↗
2026

LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models

Alvi Md Ishmam, Najibul Haque Sarker, Zaber Ibn Abdul Hakim, Chris Thomas
AAAI 2026technical

Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs remain unexplored. Existing adversarial attacks focus on single-i

Cited by 0Source ↗PDF ↗Scholar ↗
2025

SONICS: Synthetic Or Not - Identifying Counterfeit Songs

Md Awsafur Rahman, Zaber Ibn Abdul Hakim, Najibul Haque Sarker, Bishmoy Paul, Shaikh Anowarul Fattah
ICLR 2025poster

The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song d…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2025

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models

Anushka Sivakumar, Andrew Zhang, Zaber Ibn Abdul Hakim, Chris Thomas
EMNLP 2025

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts encoding target and converse behaviors to dynamically adjust activ

Cited by 0Source ↗PDF ↗Scholar ↗