Picture for Adnan Siraj Rakin

Adnan Siraj Rakin

DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack

May 14, 2023
Figure 1 for DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack
Figure 2 for DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack
Figure 3 for DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack
Figure 4 for DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack
Viaarxiv icon

Model Extraction Attacks on Split Federated Learning

Mar 13, 2023
Figure 1 for Model Extraction Attacks on Split Federated Learning
Figure 2 for Model Extraction Attacks on Split Federated Learning
Figure 3 for Model Extraction Attacks on Split Federated Learning
Figure 4 for Model Extraction Attacks on Split Federated Learning
Viaarxiv icon

ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning

Add code
May 09, 2022
Figure 1 for ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
Figure 2 for ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
Figure 3 for ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
Figure 4 for ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
Viaarxiv icon

DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories

Nov 08, 2021
Figure 1 for DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Figure 2 for DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Figure 3 for DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Figure 4 for DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Viaarxiv icon

RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy

Add code
Mar 22, 2021
Figure 1 for RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Figure 2 for RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Figure 3 for RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Figure 4 for RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Viaarxiv icon

RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery

Jan 20, 2021
Figure 1 for RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
Figure 2 for RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
Figure 3 for RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
Figure 4 for RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
Viaarxiv icon

DA2: Deep Attention Adapter for Memory-EfficientOn-Device Multi-Domain Learning

Dec 02, 2020
Figure 1 for DA2: Deep Attention Adapter for Memory-EfficientOn-Device Multi-Domain Learning
Figure 2 for DA2: Deep Attention Adapter for Memory-EfficientOn-Device Multi-Domain Learning
Figure 3 for DA2: Deep Attention Adapter for Memory-EfficientOn-Device Multi-Domain Learning
Figure 4 for DA2: Deep Attention Adapter for Memory-EfficientOn-Device Multi-Domain Learning
Viaarxiv icon

Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA

Add code
Nov 05, 2020
Figure 1 for Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Figure 2 for Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Figure 3 for Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Figure 4 for Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Viaarxiv icon

T-BFA: Targeted Bit-Flip Adversarial Weight Attack

Jul 24, 2020
Figure 1 for T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Figure 2 for T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Figure 3 for T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Figure 4 for T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Viaarxiv icon

Robust Machine Learning via Privacy/Rate-Distortion Theory

Jul 22, 2020
Figure 1 for Robust Machine Learning via Privacy/Rate-Distortion Theory
Figure 2 for Robust Machine Learning via Privacy/Rate-Distortion Theory
Viaarxiv icon