Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About Divyam
Page not in menu
This is a page not in th emain menu
Posts
Baked two bread loaves today
Published:
My mom has been baking for around seven years, so this was inevitable.
Test blog post
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
publications
A Hybrid Approach to Tiger Re-Identification
Published in ICCV 2019 Workshop (Computer Vision for Wildlife Conservation), 2019
We propose to utilize both deep learning and traditional SIFT descriptor-based matching for tiger re-identification.
WaveTransform: Crafting Adversarial Examples via Input Decomposition
Published in ECCV 2020 Workshop (Adversarial Robustness in the Real World), 2020
We introduce a novel class of adversarial attacks, namely ‘WaveTransform’, that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination).
Simulating Network Paths with Recurrent Buffering Units
Published in AAAI 2023 (Association for the Advancement of Artificial Intelligence), 2023
We developed an end-to-end network path simulation model that embeds the semantics of a physical network, leveraging domain-specific insights from physical network paths and explicitly modelling unobservable cross-traffic using a new RNN-style architecture called Recurrent Buffering Unit (RBU).
Prϵϵmpt: Sanitizing Sensitive Prompts for LLMs
Published in AAAI 2024 Workshop (Privacy-Preserving Artificial Intelligence), 2023
We introduce a cryptographically inspired notion of a prompt sanitizer which transforms an input prompt to protect its sensitive tokens.
Functional Homotopy: Smoothing Discrete Optimization Via Continous Parameters for LLM Jailbreak Attacks
Published in ICLR 2025 (International Conference on Learning Representations), 2025
This study introduces the functional homotopy method, which leverages the functional duality between model training and input generation to improve jailbreak attacks against LLMs.