
DAC-LoRA: Dynamic Adversarial Curriculum for Efficient and Robust Few-Shot Adaptation
A generalized framework that uses a dynamic, adversarial curriculum to make Vision-Language Models (VLMs) more robust against attacks, improving efficiency and few-shot adaptation

DINOHash: Learning Adversarially Robust Perceptual Hashes from Self-Supervised Features
An open-source framework for robust perceptual image hashing, DINOHash enables secure and transformation-resilient provenance detection of AI-generated images.

SPD Attack - Prevention of AI Powered Image Editing by Image Immunization
An analysis of methods to safeguard images against misuse in image-to-image editing models through reproduction and extension of existing research across various models and datasets.

From Teacher to Student: Tracking Memorization Through Model Distillation
An analysis of knowledge distillation effects on memorization in fine-tuned language models, showing that distillation from large teachers to smaller students mitigates memorization risks while improving efficiency.

Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models
In this study, we conduct a comprehensive reproducibility study of "An Image is Worth 1000 Lies: Adversarial Transferability Across Prompts on Vision-Language Models" validating the Cross-Prompt Attack (CroPA), and also proposing several key improvements to the framework.

[Re] CUDA: Curriculum of Data Augmentation for Longātailed Recognition
Using classwise degree of data augmentation to tackle class imbalance in long tailed dataset

Riemann Sum Optimization for Accurate Integrated Gradients Computation
A mathematical framework to reduce computational complexity of Integrated Gradients

A reproducability study of Important Direction Gradient Integration (IDGI)
Highlight key results or methods involved in 1-2 lines.

Rethinking Randomized Smoothing from the Perspective of Scalability
A study on randomized smoothing, analysed from the perspective of scalability as a challenge to its continued application

Image-Alchemy: Advancing Subject Fidelity in Personalized Text-to-Image Generation
A two-stage personalization pipeline for personalized image generation using LoRA-based attention fine-tuning and segmentation-guided Img2Img synthesis.

Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Models
Tree Ring Watermarks are harder to detect in modern rectified flow-based models compared to traditional diffusion models, especially under image attacks.

One Noise to Fool Them All: Universal Adversarial Defenses Against Image Editing
Image immunization involves adding undetectable noise in images to prevent editing via diffusion models. We further extended this to multiple images using a single noise.