38 citations · 241 across the 28 of their papers we have counts for
29 papers
TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge
Kurt M Wilson, Mohaiminul Al Nahian, Abeer Matar A. Almalky +5
Despite their remarkable success, machine learning models, particularly in vision applications, are alarmingly vulnerable to a range of security threats. One key factor in the atta…
Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs
Wanhao Yu, Ziyan Wang, Zheng Wang +7
Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distr…
PROTEA: Securing Robot Task Planning and Execution
Zainab Altaweel, Mohaiminul Al Nahian, Jake Juettner +2
Robots need task planning methods to generate action sequences for complex tasks. Recent work on adversarial attacks has revealed significant vulnerabilities in existing robot task…
EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
Ranyang Zhou, Abeer Matar A. Almalky, Gamana Aragonda +4
True Random Number Generators (TRNGs) play a fundamental role in hardware security, cryptographic systems, and data protection. In the context of Deep NeuralNetworks (DNNs), safegu…
Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains
Sabbir Ahmed, Mamshad Nayeem Rizve, Abdullah Al Arafat +4
Semi-Supervised Federated Learning (SSFL) is gaining popularity over conventional Federated Learning in many real-world applications. Due to the practical limitation of limited lab…
MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems
Mohaiminul Al Nahian, Zainab Altaweel, David Reitano +3
Robots need task planning methods to achieve goals that require more than one action. Recently, large pretrained models have demonstrated impressive performance in task planning. F…
Compromising the Intelligence of Modern DNNs: On the Effectiveness of Targeted RowPress
Ranyang Zhou, Jacqueline T. Liu, Sabbir Ahmed +2
Recent advancements in side-channel attacks have revealed the vulnerability of modern Deep Neural Networks (DNNs) to malicious adversarial weight attacks. The well-studied RowHamme…
Fisher Information guided Purification against Backdoor Attacks
Nazmul Karim, Abdullah Al Arafat, Adnan Siraj Rakin +2
Studies on backdoor attacks in recent years suggest that an adversary can compromise the integrity of a deep neural network (DNN) by manipulating a small set of training samples. O…
DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism
Ranyang Zhou, Jacqueline T. Liu, Nakul Kochar +3
RowHammer stands out as a prominent example, potentially the pioneering one, showcasing how a failure mechanism at the circuit level can give rise to a significant and pervasive se…
DRAM-Locker: A General-Purpose DRAM Protection Mechanism against Adversarial DNN Weight Attacks
Ranyang Zhou, Sabbir Ahmed, Arman Roohi +2
In this work, we propose DRAM-Locker as a robust general-purpose defense mechanism that can protect DRAM against various adversarial Deep Neural Network (DNN) weight attacks affect…
Threshold Breaker: Can Counter-Based RowHammer Prevention Mechanisms Truly Safeguard DRAM?
Ranyang Zhou, Jacqueline Liu, Sabbir Ahmed +3
This paper challenges the existing victim-focused counter-based RowHammer detection mechanisms by experimentally demonstrating a novel multi-sided fault injection attack technique…
DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs
Ranyang Zhou, Sabbir Ahmed, Adnan Siraj Rakin +1
With deep learning deployed in many security-sensitive areas, machine learning security is becoming progressively important. Recent studies demonstrate attackers can exploit system…
Model Extraction Attacks on Split Federated Learning
Jingtao Li, Adnan Siraj Rakin, Xing Chen +4
Federated Learning (FL) is a popular collaborative learning scheme involving multiple clients and a server. FL focuses on protecting clients' data but turns out to be highly vulner…
ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
Jingtao Li, Adnan Siraj Rakin, Xing Chen +3
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 activat…
DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories
Adnan Siraj Rakin, Md Hafizul Islam Chowdhuryy, Fan Yao +1
Recent advancements of Deep Neural Networks (DNNs) have seen widespread deployment in multiple security-sensitive domains. The need of resource-intensive training and use of valuab…
NeurObfuscator: A Full-stack Obfuscation Tool to Mitigate Neural Architecture Stealing
Jingtao Li, Zhezhi He, Adnan Siraj Rakin +2
Neural network stealing attacks have posed grave threats to neural network model deployment. Such attacks can be launched by extracting neural architecture information, such as lay…
RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy
Adnan Siraj Rakin, Li Yang, Jingtao Li +5
Recently developed adversarial weight attack, a.k.a. bit-flip attack (BFA), has shown enormous success in compromising Deep Neural Network (DNN) performance with an extremely small…
RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery
Jingtao Li, Adnan Siraj Rakin, Zhezhi He +2
Adversarial attacks on Neural Network weights, such as the progressive bit-flip attack (PBFA), can cause a catastrophic degradation in accuracy by flipping a very small number of b…
:Dynamic Additive Attention Adaption for Memory-EfficientOn-Device Multi-Domain Learning
Li Yang, Adnan Siraj Rakin, Deliang Fan
Nowadays, one practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). It motivates researchers…
Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA
Adnan Siraj Rakin, Yukui Luo, Xiaolin Xu +1
The wide deployment of Deep Neural Networks (DNN) in high-performance cloud computing platforms brought to light multi-tenant cloud field-programmable gate arrays (FPGA) as a popul…
T-BFA: Targeted Bit-Flip Adversarial Weight Attack
Adnan Siraj Rakin, Zhezhi He, Jingtao Li +3
Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, atta…
Robust Machine Learning via Privacy/Rate-Distortion Theory
Ye Wang, Shuchin Aeron, Adnan Siraj Rakin +2
Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between opti…
DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips
Fan Yao, Adnan Siraj Rakin, Deliang Fan
Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have…
TBT: Targeted Neural Network Attack with Bit Trojan
Adnan Siraj Rakin, Zhezhi He, Deliang Fan
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,…