Picture for Thorsten Eisenhofer

Thorsten Eisenhofer

Whispers in the Machine: Confidentiality in LLM-integrated Systems

Add code
Feb 10, 2024
Viaarxiv icon

A Representative Study on Human Detection of Artificially Generated Media Across Countries

Add code
Dec 10, 2023
Figure 1 for A Representative Study on Human Detection of Artificially Generated Media Across Countries
Figure 2 for A Representative Study on Human Detection of Artificially Generated Media Across Countries
Figure 3 for A Representative Study on Human Detection of Artificially Generated Media Across Countries
Figure 4 for A Representative Study on Human Detection of Artificially Generated Media Across Countries
Viaarxiv icon

On the Limitations of Model Stealing with Uncertainty Quantification Models

Add code
May 09, 2023
Figure 1 for On the Limitations of Model Stealing with Uncertainty Quantification Models
Figure 2 for On the Limitations of Model Stealing with Uncertainty Quantification Models
Figure 3 for On the Limitations of Model Stealing with Uncertainty Quantification Models
Viaarxiv icon

No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning

Add code
Mar 25, 2023
Figure 1 for No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
Figure 2 for No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
Figure 3 for No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
Figure 4 for No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
Viaarxiv icon

Learned Systems Security

Add code
Jan 10, 2023
Figure 1 for Learned Systems Security
Figure 2 for Learned Systems Security
Figure 3 for Learned Systems Security
Figure 4 for Learned Systems Security
Viaarxiv icon

Verifiable and Provably Secure Machine Unlearning

Add code
Oct 17, 2022
Figure 1 for Verifiable and Provably Secure Machine Unlearning
Figure 2 for Verifiable and Provably Secure Machine Unlearning
Figure 3 for Verifiable and Provably Secure Machine Unlearning
Figure 4 for Verifiable and Provably Secure Machine Unlearning
Viaarxiv icon

Dompteur: Taming Audio Adversarial Examples

Add code
Feb 10, 2021
Figure 1 for Dompteur: Taming Audio Adversarial Examples
Figure 2 for Dompteur: Taming Audio Adversarial Examples
Figure 3 for Dompteur: Taming Audio Adversarial Examples
Figure 4 for Dompteur: Taming Audio Adversarial Examples
Viaarxiv icon

VENOMAVE: Clean-Label Poisoning Against Speech Recognition

Add code
Oct 21, 2020
Figure 1 for VENOMAVE: Clean-Label Poisoning Against Speech Recognition
Figure 2 for VENOMAVE: Clean-Label Poisoning Against Speech Recognition
Figure 3 for VENOMAVE: Clean-Label Poisoning Against Speech Recognition
Figure 4 for VENOMAVE: Clean-Label Poisoning Against Speech Recognition
Viaarxiv icon

Leveraging Frequency Analysis for Deep Fake Image Recognition

Add code
Mar 20, 2020
Figure 1 for Leveraging Frequency Analysis for Deep Fake Image Recognition
Figure 2 for Leveraging Frequency Analysis for Deep Fake Image Recognition
Figure 3 for Leveraging Frequency Analysis for Deep Fake Image Recognition
Figure 4 for Leveraging Frequency Analysis for Deep Fake Image Recognition
Viaarxiv icon