Guillaume Leclerc
7 papers · 2022–2023 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (9) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(21)
π£
Hot Topic Early Bird
Conferences
ICML (5)
CVPR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
influence function
(2)
adversarial perturbation
(2)
adversarial robustness
(1)
data poisoning
(1)
computer vision
(1)
robust statistics
(1)
model analysis
(1)
neural representation
(1)
feature attribution
(1)
efficient computing
(1)
data representation
(1)
feature representation
(1)
model debugging
(1)
outlier detection
(1)
machine learning security
(1)
image editing
(1)
backdoor attack
(1)
random projection
(1)
diffusion model
(1)
image generation
(1)
Papers
Rethinking Backdoor Attacks
ICML 2023
TRAK: Attributing Model Behavior at Scale
ICML 2023
Raising the Cost of Malicious AI-Powered Image Editing
ICML 2023
FFCV: Accelerating Training by Removing Data Bottlenecks
CVPR 2023
Datamodels: Understanding Predictions with Data and Data with Predictions
ICML 2022
Adversarially trained neural representations may already be as robust as corresponding biological neural representations
ICML 2022
3DB: A Framework for Debugging Computer Vision Models
NIPS 2022