Picture for Arezoo Rajabi

Arezoo Rajabi

Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors

Add code
Feb 12, 2024
Viaarxiv icon

Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization

Add code
Feb 02, 2024
Viaarxiv icon

MDTD: A Multi Domain Trojan Detector for Deep Neural Networks

Add code
Sep 03, 2023
Viaarxiv icon

LDL: A Defense for Label-Based Membership Inference Attacks

Add code
Dec 16, 2022
Viaarxiv icon

Game of Trojans: A Submodular Byzantine Approach

Add code
Jul 13, 2022
Figure 1 for Game of Trojans: A Submodular Byzantine Approach
Figure 2 for Game of Trojans: A Submodular Byzantine Approach
Figure 3 for Game of Trojans: A Submodular Byzantine Approach
Figure 4 for Game of Trojans: A Submodular Byzantine Approach
Viaarxiv icon

Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning

Add code
Mar 25, 2022
Figure 1 for Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
Figure 2 for Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
Figure 3 for Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
Figure 4 for Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
Viaarxiv icon

Privacy-Preserving Reinforcement Learning Beyond Expectation

Add code
Mar 18, 2022
Figure 1 for Privacy-Preserving Reinforcement Learning Beyond Expectation
Figure 2 for Privacy-Preserving Reinforcement Learning Beyond Expectation
Figure 3 for Privacy-Preserving Reinforcement Learning Beyond Expectation
Viaarxiv icon

Adversarial Profiles: Detecting Out-Distribution & Adversarial Samples in Pre-trained CNNs

Add code
Nov 18, 2020
Figure 1 for Adversarial Profiles: Detecting Out-Distribution & Adversarial Samples in Pre-trained CNNs
Figure 2 for Adversarial Profiles: Detecting Out-Distribution & Adversarial Samples in Pre-trained CNNs
Viaarxiv icon

Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks

Add code
May 17, 2020
Figure 1 for Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks
Figure 2 for Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks
Figure 3 for Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks
Figure 4 for Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks
Viaarxiv icon

Toward Metrics for Differentiating Out-of-Distribution Sets

Add code
Oct 18, 2019
Figure 1 for Toward Metrics for Differentiating Out-of-Distribution Sets
Figure 2 for Toward Metrics for Differentiating Out-of-Distribution Sets
Figure 3 for Toward Metrics for Differentiating Out-of-Distribution Sets
Figure 4 for Toward Metrics for Differentiating Out-of-Distribution Sets
Viaarxiv icon