Atul Prakash
13 papers · 2018–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (7) π Academic Marathon (7)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(14)
π
Century Club
(13)
β‘
Prolific Year
(5)
Conferences
ICLR (4)
CVPR (3)
ICML (2)
ACL (1)
ECCV (1)
NIPS (1)
WACV (1)
Top co-authors
Research topics
Keywords
adversarial perturbation
(3)
adversarial example
(2)
large language model
(2)
deep neural network
(2)
adversarial training
(1)
ai safety
(1)
gradient estimation
(1)
distribution shift
(1)
structured sparsity
(1)
training efficiency
(1)
adversarial attack
(1)
black-box attack
(1)
generative model
(1)
synthetic datum
(1)
zeroth-order optimization
(1)
out-of-distribution detection
(1)
jailbreak attack
(1)
inference efficiency
(1)
transferable adversarial example
(1)
activation sparsity
(1)
Papers
Test-Time Canonicalization by Foundation Models for Robust Perception
ICML 2025
ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
ICLR 2025
Learn To be Efficient: Build Structured Sparsity in Large Language Models
NIPS 2024
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
ACL 2024
Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
ECCV 2024
CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
ICLR 2024
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles
WACV 2024
Coverage-centric Coreset Selection for High Pruning Rates
ICLR 2023
Concept-based Explanations for Out-of-Distribution Detectors
ICML 2023
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation
CVPR 2021
Protecting DNNs from Theft using an Ensemble of Diverse Models
ICLR 2021
Efficient Adversarial Training With Transferable Adversarial Examples
CVPR 2020
Robust Physical-World Attacks on Deep Learning Visual Classification
CVPR 2018