Gaurang Sriramanan
9 papers · 2020–2025 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (24) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver
🧬
Topic Evolution
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(7)
Learning Types · Machine Learning
(7)
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(4)
Natural Language Processing
(2)
Application Areas
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Resources & Methods
(2)
Techniques
(2)
Computer Science
(1)
Computer Vision
(1)
Analysis
(1)
Keywords
adversarial attack
(5)
adversarial training
(4)
large language model
(3)
adversarial robustness
(3)
deep neural network
(2)
cross-entropy loss
(1)
prompt engineering
(1)
domain adaptation
(1)
hidden state
(1)
white-box setting
(1)
model robustness
(1)
adversarial defense
(1)
projected gradient descent
(1)
vision model
(1)
retrieval-augmented generation
(1)
tool selection
(1)
hallucination detection
(1)
internal state analysis
(1)
neural network optimization
(1)
computer vision
(1)
Papers
Tool Preferences in Agentic LLMs are Unreliable
EMNLP 2025
Fast Adversarial Attacks on Language Models In One GPU Minute
ICML 2024
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
NeurIPS 2024
Exploring Geometry of Blind Spots in Vision models
NeurIPS 2023
Scaling Adversarial Training to Large Perturbation Bounds
ECCV 2022
Toward Efficient Robust Training against Union of ℓ_p Threat Models
NeurIPS 2022
Towards Efficient and Effective Adversarial Training
NeurIPS 2021
Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
NeurIPS 2020
Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes
CVPR 2020