Lukas Struppek
7 papers · 2022–2024 · 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
(15)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(5)
Artificial Intelligence
(4)
Application Areas
(4)
Core AI
(4)
Learning Types · Machine Learning
(4)
Models
(4)
Computer Vision
(2)
Generation
(2)
Security & Privacy
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Privacy
(1)
Processing
(1)
Keywords
deep learning
(2)
model inversion attack
(2)
diffusion model
(2)
text-to-image synthesis
(2)
stable diffusion
(2)
generative adversarial network
(2)
neural network interpretability
(1)
label smoothing
(1)
distribution shift
(1)
backdoor attack
(1)
generative model
(1)
out-of-distribution detection
(1)
controllable generation
(1)
classifier-free guidance
(1)
text-to-image diffusion
(1)
distributional shift
(1)
privacy protection
(1)
privacy leakage
(1)
cultural bia
(1)
text encoder
(1)
Papers
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
ICLR 2024
Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)
IJCAI 2024
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
NeurIPS 2024
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
ICCV 2023
SEGA: Instructing Text-to-Image Models using Semantic Guidance
NeurIPS 2023
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
ICML 2022
To Trust or Not To Trust Prediction Scores for Membership Inference Attacks
IJCAI 2022