25 citations · 74 across the 41 of their papers we have counts for
7 papers · 1 filter
Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation
B. Ghosh, H. Harikumar, S. Rana
Nearest-neighbour retrieval is central to classification and explainable-AI pipelines, but current practice relies on hand-tuning feature layers and distance metrics. We propose Ta…
Composite Concept Extraction through Backdooring
Banibrata Ghosh, Haripriya Harikumar, Khoa D Doan +2
Learning composite concepts, such as \textquotedbl red car\textquotedbl , from individual examples -- like a white car representing the concept of \textquotedbl car\textquotedbl{}…
Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
Kien Do, Hung Le, Dung Nguyen +5
Data-free Knowledge Distillation (DFKD) has attracted attention recently thanks to its appealing capability of transferring knowledge from a teacher network to a student network wi…
Defense Against Multi-target Trojan Attacks
Haripriya Harikumar, Santu Rana, Kien Do +4
Adversarial attacks on deep learning-based models pose a significant threat to the current AI infrastructure. Among them, Trojan attacks are the hardest to defend against. In this…
Semantic Host-free Trojan Attack
Haripriya Harikumar, Kien Do, Santu Rana +2
In this paper, we propose a novel host-free Trojan attack with triggers that are fixed in the semantic space but not necessarily in the pixel space. In contrast to existing Trojan…
Logically Consistent Loss for Visual Question Answering
Anh-Cat Le-Ngo, Truyen Tran, Santu Rana +2
Given an image, a back-ground knowledge, and a set of questions about an object, human learners answer the questions very consistently regardless of question forms and semantic tas…