14 citations · 27 across the 13 of their papers we have counts for
13 papers
ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models
Hashmat Shadab Malik, Toluwani Aremu, Samuele Poppi +2
Training-free test-time defenses offer a practical way to improve the adversarial robustness of CLIP-style vision--language models without modifying the pretrained model. However,…
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior work on MLLM…
Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models
Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
Vision-language models (VLMs) such as CLIP show strong zero-shot generalization but remain highly vulnerable to adversarial attacks. Adversarial training improves robustness but is…
Investigating Adversarial Robustness of Multi-modal Large Language Models
Hashmat Shadab Malik, Muzammal Naseer, Salman Khan
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially e…
Sentence-level Prompts Benefit Composed Image Retrieval
Yang Bai, Xinxing Xu, Yong Liu +5
Composed image retrieval (CIR) is the task of retrieving specific images by using a query that involves both a reference image and a relative caption. Most existing CIR models adop…
3D Indoor Instance Segmentation in an Open-World
Mohamed El Amine Boudjoghra, Salwa K. Al Khatib, Jean Lahoud +4
Existing 3D instance segmentation methods typically assume that all semantic classes to be segmented would be available during training and only seen categories are segmented at in…
Towards Instance-adaptive Inference for Federated Learning
Chun-Mei Feng, Kai Yu, Nian Liu +3
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. However, the performance of…
Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning
Chun-Mei Feng, Kai Yu, Yong Liu +2
Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper…
Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
Sheng Zhang, Muzammal Naseer, Guangyi Chen +4
Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. Despite the success, most traditional VLMs-based methods are restricted by…
Boosting Adversarial Transferability using Dynamic Cues
Muzammal Naseer, Ahmad Mahmood, Salman Khan +1
The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet tr…
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery
Sheng Zhang, Salman Khan, Zhiqiang Shen +3
Although existing semi-supervised learning models achieve remarkable success in learning with unannotated in-distribution data, they mostly fail to learn on unlabeled data sampled…
CLIP model is an Efficient Continual Learner
Vishal Thengane, Salman Khan, Munawar Hayat +1
The continual learning setting aims to learn new tasks over time without forgetting the previous ones. The literature reports several significant efforts to tackle this problem wit…
D3Former: Debiased Dual Distilled Transformer for Incremental Learning
Abdelrahman Mohamed, Rushali Grandhe, K J Joseph +2
In class incremental learning (CIL) setting, groups of classes are introduced to a model in each learning phase. The goal is to learn a unified model performant on all the classes…