Adnan Siraj Rakin — accepted AI-conference papers

2026

Unleashing Stealthy Backdoor Pandemic by Infecting a Single Diffusion Model

Mohaiminul Al Nahian, Abeer Matar Almalky, Sabbir Ahmed, Abdullah Al Arafat, Mamshad Nayeem Rizve, Adnan Siraj Rakin

CVPR 2026

The remarkable success of modern Deep Neural Networks (DNNs) can be primarily attributed to having access to compute resources and high-quality labeled data, which is often costly and challenging to acquire. Recently, text-to-image Diffusion Models (DMs) have emerged as powerful data generators to a

Cited by 0 Source ↗code ↗Scholar ↗

2025

DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge

Sabbir Ahmed, Abdullah Al Arafat, Deniz Najafi, Akhlak Mahmood, Mamshad Nayeem Rizve, Mohaiminul Al Nahian +3

CVPR 2025poster

Vision Transformers (ViTs) excel in tackling complex vision tasks, yet their substantial size poses significant challenges for applications on resource-constrained edge devices. The increased size of these models leads to higher overhead (e.g., energy, latency) when transmitting model weights betwee…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack

Sabbir Ahmed, Ranyang Zhou, Shaahin Angizi, Adnan Siraj Rakin

CVPR 2024poster

To insert Trojan into a Deep Neural Network (DNN) the existing attack assumes the attacker can access the victim's training facilities. However a realistic threat model was recently developed by leveraging memory fault to inject Trojans at the inference stage. In this work we develop a novel Trojan…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2024

EMGAN: Early-Mix-GAN on Extracting Server-Side Model in Split Federated Learning

Jingtao Li, Xing Chen, Li Yang, Adnan Siraj Rakin, Deliang Fan, Chaitali Chakrabarti

AAAI 2024technical

Split Federated Learning (SFL) is an emerging edge-friendly version of Federated Learning (FL), where clients process a small portion of the entire model. While SFL was considered to be resistant to Model Extraction Attack (MEA) by design, a recent work shows it is not necessarily the case. In gener…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

SSDA: Secure Source-Free Domain Adaptation

Sabbir Ahmed, Abdullah Al Arafat, Mamshad Nayeem Rizve, Rahim Hossain, Zhishan Guo, Adnan Siraj Rakin

ICCV 2023poster

Source-free domain adaptation (SFDA) is a popular unsupervised domain adaptation method where a pre-trained model from a source domain is adapted to a target domain without accessing any source data. Despite rich results in this area, existing literature overlooks the security challenges of the unsu…

Cited by 11 PDF ↗code ↗Scholar ↗

2022

Rep-Net: Efficient On-Device Learning via Feature Reprogramming

Li Yang, Adnan Siraj Rakin, Deliang Fan

CVPR 2022poster

Transfer learning, where the goal is to transfer the well-trained deep learning models from a primary source task to a new task, is a crucial learning scheme for on-device machine learning, due to the fact that IoT/edge devices collect and then process massive data in our daily life. However, due to…

Cited by 31 PDF ↗Scholar ↗

2022

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

Jingtao Li, Adnan Siraj Rakin, Xing Chen, Zhezhi He, Deliang Fan, Chaitali Chakrabarti

CVPR 2022poster

This work aims to tackle Model Inversion (MI) attack on Split Federated Learning (SFL). SFL is a recent distributed training scheme where multiple clients send intermediate activations (i.e., feature map), instead of raw data, to a central server. While such a scheme helps reduce the computational l…

Cited by 81 PDF ↗code ↗Scholar ↗

2020

Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack

Zhezhi He, Adnan Siraj Rakin, Jingtao Li, Chaitali Chakrabarti, Deliang Fan

CVPR 2020poster

Recently, a new paradigm of the adversarial attack on the quantized neural network weights has attracted great attention, namely, the Bit-Flip based adversarial weight attack, aka. Bit-Flip Attack (BFA). BFA has shown extraordinary attacking ability, where the adversary can malfunction a quantized D…

Cited by 108 PDF ↗code ↗Scholar ↗

2020

TBT: Targeted Neural Network Attack With Bit Trojan

Adnan Siraj Rakin, Zhezhi He, Deliang Fan

CVPR 2020poster

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively infect the model during the training phase and get activated only…

Cited by 293 PDF ↗code ↗Scholar ↗

2019

Bit-Flip Attack: Crushing Neural Network With Progressive Bit Search

Adnan Siraj Rakin, Zhezhi He, Deliang Fan

ICCV 2019poster

Several important security issues of Deep Neural Network (DNN) have been raised recently associated with different applications and components. The most widely investigated security concern of DNN is from its malicious input, a.k.a adversarial example. Nevertheless, the security challenge of DNN's p…

Cited by 331 PDF ↗code ↗Scholar ↗

2019

Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack

Zhezhi He, Adnan Siraj Rakin, Deliang Fan

CVPR 2019poster

Recent developments in the field of Deep Learning have exposed the underlying vulnerability of Deep Neural Network (DNN) against adversarial examples. In image classification, an adversarial example is a carefully modified image that is visually imperceptible to the original image but can cause DNN…

Cited by 368 PDF ↗code ↗Scholar ↗