Adnan Siraj Rakin

Orcid: 0000-0002-6056-2625

According to our database1, Adnan Siraj Rakin authored at least 41 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Fisher Information guided Purification against Backdoor Attacks.
CoRR, 2024

DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism.
CoRR, 2024

DeepShuffle: A Lightweight Defense Framework against Adversarial Fault Injection Attacks on Deep Neural Networks in Multi-Tenant Cloud-FPGA.
Proceedings of the IEEE Symposium on Security and Privacy, 2024

DRAM-Locker: A General-Purpose DRAM Protection Mechanism Against Adversarial DNN Weight Attacks.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2024

DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs.
Proceedings of the 61st ACM/IEEE Design Automation Conference, 2024

Deep-TROJ: An Inference Stage Trojan Insertion Algorithm Through Efficient Weight Replacement Attack.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

EMGAN: Early-Mix-GAN on Extracting Server-Side Model in Split Federated Learning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Threshold Breaker: Can Counter-Based RowHammer Prevention Mechanisms Truly Safeguard DRAM?
CoRR, 2023

DNN-Defender: An in-DRAM Deep Neural Network Defense Mechanism for Adversarial Weight Attack.
CoRR, 2023

Model Extraction Attacks on Split Federated Learning.
CoRR, 2023

SSDA: Secure Source-Free Domain Adaptation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
T-BFA: Targeted Bit-Flip Adversarial Weight Attack.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Improving DNN Hardware Accuracy by In-Memory Computing Noise Injection.
IEEE Des. Test, 2022

DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories.
Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022

RepNet: Efficient On-Device Learning via Feature Reprogramming.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

DA<sup>3</sup>: Dynamic Additive Attention Adaption for Memory-Efficient On-Device Multi-Domain Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy.
CoRR, 2021

Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA.
Proceedings of the 30th USENIX Security Symposium, 2021

Towards Universal Adversarial Examples and Defenses.
Proceedings of the IEEE Information Theory Workshop, 2021

Robust Machine Learning via Privacy/ Rate-Distortion Theory.
Proceedings of the IEEE International Symposium on Information Theory, 2021

NeurObfuscator: A Full-stack Obfuscation Tool to Mitigate Neural Architecture Stealing.
Proceedings of the IEEE International Symposium on Hardware Oriented Security and Trust, 2021

RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2021

Leveraging Noise and Aggressive Quantization of In-Memory Computing for Robust DNN Hardware Against Adversarial Input and Weight Attacks.
Proceedings of the 58th ACM/IEEE Design Automation Conference, 2021

2020
Sparse BD-Net: A Multiplication-less DNN with Sparse Binarized Depth-wise Separable Convolution.
ACM J. Emerg. Technol. Comput. Syst., 2020

DA2: Deep Attention Adapter for Memory-EfficientOn-Device Multi-Domain Learning.
CoRR, 2020

DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips.
Proceedings of the 29th USENIX Security Symposium, 2020

Robust Sparse Regularization: Defending Adversarial Attacks Via Regularized Sparse Network.
Proceedings of the GLSVLSI '20: Great Lakes Symposium on VLSI 2020, 2020

Defending Bit-Flip Attack through DNN Weight Reconstruction.
Proceedings of the 57th ACM/IEEE Design Automation Conference, 2020

TBT: Targeted Neural Network Attack With Bit Trojan.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness.
CoRR, 2019

Bit-Flip Attack: Crushing Neural Network withProgressive Bit Search.
CoRR, 2019

Defense-Net: Defend Against a Wide Range of Adversarial Attacks through Adversarial Detector.
Proceedings of the 2019 IEEE Computer Society Annual Symposium on VLSI, 2019

Bit-Flip Attack: Crushing Neural Network With Progressive Bit Search.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018
Defend Deep Neural Networks Against Adversarial Examples via Fixed andDynamic Quantized Activation Functions.
CoRR, 2018

Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples.
CoRR, 2018

BD-NET: A Multiplication-Less DNN with Binarized Depthwise Separable Convolution.
Proceedings of the 2018 IEEE Computer Society Annual Symposium on VLSI, 2018

PIM-TGAN: A Processing-in-Memory Accelerator for Ternary Generative Adversarial Networks.
Proceedings of the 36th IEEE International Conference on Computer Design, 2018

CMP-PIM: an energy-efficient comparator-based processing-in-memory neural network accelerator.
Proceedings of the 55th Annual Design Automation Conference, 2018


  Loading...