4 papers
MI-to-Mid Distilled Compression (M2M-DC): An Hybrid-Information-Guided-Block Pruning with Progressive Inner Slicing Approach to Model Compression
Lionel Levine, Haniyeh Ehsani Oskouie, Sajjad Ghiasvand +1
We introduce MI-to-Mid Distilled Compression (M2M-DC), a two-scale, shape-safe compression framework that interleaves information-guided block pruning with progressive inner slicin…
Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie +3
We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods…
Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models
Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh +1
Vision-Language Models (VLMs) such as CLIP have shown remarkable performance in cross-modal tasks through large-scale contrastive pre-training. To adapt these large transformer-bas…
Leveraging Large Language Models and Topic Modeling for Toxicity Classification
Haniyeh Ehsani Oskouie, Christina Chance, Claire Huang +3
Content moderation and toxicity classification represent critical tasks with significant social implications. However, studies have shown that major classification models exhibit t…