Lukas Struppek
7 papers · 2022–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π Cross-Pollinator (10) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(13)
π£
Hot Topic Early Bird
Conferences
IJCAI (2)
NIPS (2)
ICCV (1)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
generative adversarial network
(2)
stable diffusion
(2)
diffusion model
(2)
text-to-image synthesis
(2)
text-to-image generation
(1)
responsible ai
(1)
neural network interpretability
(1)
deep learning
(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)
model inversion attack
(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
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
NIPS 2024
Exploiting Cultural Biases via Homoglyphs inText-to-Image Synthesis (Abstract Reprint)
IJCAI 2024
SEGA: Instructing Text-to-Image Models using Semantic Guidance
NIPS 2023
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
ICCV 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