Ashish Kundu
8 papers · 2022–2026 · 6 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
(15)
🔥
Unstoppable · Bronze
📈
Trend Setter
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(5)
Core AI
(5)
Application Areas
(4)
Learning Types · Machine Learning
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Data Science & Analytics
(1)
Deep Learning
(1)
Applications · Data Science & Analytics
(1)
Applications · Natural Language Processing
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Resources & Methods
(1)
Keywords
poisoning attack
(3)
adversarial robustness
(2)
backdoor attack
(2)
large language model
(2)
false positive rate
(1)
domain knowledge
(1)
adversarial attack
(1)
generative model
(1)
latent representation
(1)
language model
(1)
feature engineering
(1)
watermark detection
(1)
user feedback
(1)
retrieval-augmented generation
(1)
refusal behavior
(1)
recommender system
(1)
tabular prediction
(1)
policy enforcement
(1)
kernel-based learning
(1)
backdoor detection
(1)
Papers
Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models
EACL 2026
AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
EMNLP 2025
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
ICML 2025
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
ICLR 2024
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
NeurIPS 2024
A Unified Detection Framework for Inference-Stage Backdoor Defenses
NeurIPS 2023
Understanding Backdoor Attacks through the Adaptability Hypothesis
ICML 2023
BeautifAI - Personalised Occasion-based Makeup
Recommendation
ACML 2022