Vinu Sankar Sadasivan
7 papers · 2019–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5)
π£
Hot Topic Early Bird
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(6)
π
Triple Crown
Conferences
NIPS (3)
CVPR (1)
EACL (1)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
adversarial attack
(2)
computer vision
(1)
model robustness
(1)
adversarial training
(1)
data privacy
(1)
hidden state
(1)
deep neural network
(1)
vision model
(1)
retrieval-augmented generation
(1)
hallucination detection
(1)
internal state analysis
(1)
white-box setting
(1)
black-box setting
(1)
hidden state analysis
(1)
attention map
(1)
audio perturbation
(1)
large language model
(1)
model vulnerability
(1)
level set
(1)
consistency checking
(1)
Papers
Attackerβs Noise Can Manipulate Your Audio-based LLM in the Real World
EACL 2026
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 2024
Fast Adversarial Attacks on Language Models In One GPU Minute
ICML 2024
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
NIPS 2024
CUDA: Convolution-Based Unlearnable Datasets
CVPR 2023
Exploring Geometry of Blind Spots in Vision models
NIPS 2023
Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices
NIPS 2019