Picture for N. Asokan

N. Asokan

Espresso: Robust Concept Filtering in Text-to-Image Models

Add code
May 01, 2024
Viaarxiv icon

SoK: Unintended Interactions among Machine Learning Defenses and Risks

Add code
Dec 07, 2023
Viaarxiv icon

Attesting Distributional Properties of Training Data for Machine Learning

Add code
Aug 18, 2023
Viaarxiv icon

FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks

Add code
Jul 27, 2023
Viaarxiv icon

False Claims against Model Ownership Resolution

Add code
Apr 28, 2023
Viaarxiv icon

GrOVe: Ownership Verification of Graph Neural Networks using Embeddings

Add code
Apr 17, 2023
Viaarxiv icon

On the Robustness of Dataset Inference

Add code
Oct 24, 2022
Viaarxiv icon

Conflicting Interactions Among Protections Mechanisms for Machine Learning Models

Add code
Jul 05, 2022
Figure 1 for Conflicting Interactions Among Protections Mechanisms for Machine Learning Models
Figure 2 for Conflicting Interactions Among Protections Mechanisms for Machine Learning Models
Figure 3 for Conflicting Interactions Among Protections Mechanisms for Machine Learning Models
Figure 4 for Conflicting Interactions Among Protections Mechanisms for Machine Learning Models
Viaarxiv icon

On the Effectiveness of Dataset Watermarking in Adversarial Settings

Add code
Feb 25, 2022
Figure 1 for On the Effectiveness of Dataset Watermarking in Adversarial Settings
Figure 2 for On the Effectiveness of Dataset Watermarking in Adversarial Settings
Figure 3 for On the Effectiveness of Dataset Watermarking in Adversarial Settings
Figure 4 for On the Effectiveness of Dataset Watermarking in Adversarial Settings
Viaarxiv icon

Do Transformers use variable binding?

Add code
Feb 19, 2022
Figure 1 for Do Transformers use variable binding?
Figure 2 for Do Transformers use variable binding?
Figure 3 for Do Transformers use variable binding?
Figure 4 for Do Transformers use variable binding?
Viaarxiv icon