Ashish Hooda
5 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI · Artificial Intelligence
(4)
Machine Learning
(3)
Learning Types · Machine Learning
(3)
Deep Learning
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Application Areas
(1)
Architectures
(1)
Core AI · Computer Vision
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Optimization
(1)
Keywords
jailbreak attack
(2)
large language model
(2)
model safety
(1)
deep learning
(1)
ai safety
(1)
discrete optimization
(1)
deep learning model
(1)
adversarial attack
(1)
homotopy method
(1)
adversarial perturbation
(1)
adversarial example
(1)
control flow
(1)
guard model
(1)
physical adversarial attack
(1)
rolling shutter
(1)
counterfactual analysis
(1)
physical attack
(1)
frequency spectrum analysis
(1)
black-box access
(1)
data flow
(1)
Papers
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
ICLR 2025
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles
WACV 2024
Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
ICML 2024
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
ACL 2024
Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect
CVPR 2021