Adnan Siraj Rakin

Adnan Siraj Rakin

Auto-generated profile, based on publicly available information

Adnan Siraj Rakin

Binghamton University, Binghamton, NY, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 September 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ARAdnan Siraj Rakin
Adnan Siraj Rakin
ZHZhezhi He
Zhezhi He
JLJingtao Li
Jingtao Li
FYFan Yao
Fan Yao
CCChaitali Chakrabarti
Chaitali Chakrabarti
DFDeliang Fan
Deliang Fan
Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. As a representative one, the Bit-Flip-based adversarial weight Attack (BFA) injects an extremely small amount of faults into weight parameters to hijack the executing DNN function. Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory. This paper proposes the first work of targeted BFA based (T-BFA) adversarial weight attack on DNNs, which can intentionally mislead selected inputs to a target output class. The objective is achieved by identifying the weight bits that are highly associated with classification of a targeted output through a class-dependent vulnerable weight bit searching algorithm. Our proposed T-BFA performance is successfully demonstrated on multiple DNN architectures for image classification tasks. For example, by merely flipping 27 out of 88 million weight bits of ResNet-18, our T-BFA can misclassify all the images from ’Hen’ class into ’Goose’ class (i.e., 100% attack success rate) in ImageNet dataset, while maintaining 59.35% validation accuracy. Moreover, we successfully demonstrate our T-BFA attack in a real computer prototype system running DNN computation, with Ivy Bridge-based Intel i7 CPU and 8GB DDR3 memory.

12 December 2021
Verified
Conference Paper
Closed access
JLJingtao Li
Jingtao Li
Zhezhi HeZhezhi He
Zhezhi He
ARAdnan Siraj Rakin
Adnan Siraj Rakin
DFDeliang Fan
Deliang Fan
CCChaitali Chakrabarti
Chaitali Chakrabarti
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 layer sequence and dimension parameters, through leaky side-channels. To mitigate such attacks, we propose NeurObfuscator, a full-stack obfuscation tool to obfuscate the neural network architecture while preserving its functionality with very limited performance overhead. At the heart of this tool is a set of obfuscating knobs, including layer branching, layer widening, selective fusion and schedule pruning, that increase the number of operators, reduce/increase the latency, and number of cache and DRAM accesses. A genetic algorithm-based approach is adopted to orchestrate the combination of obfuscating knobs to achieve the best obfuscating effect on the layer sequence and dimension parameters so that the architecture information cannot be successfully extracted. Results on sequence obfuscation show that the proposed tool obfuscates a ResNet-18 ImageNet model to a totally different architecture (with 44 layer difference) without affecting its functionality with only 2% overall latency overhead. For dimension obfuscation, we demonstrate that an example convolution layer with 64 input and 128 output channels can be obfuscated to generate a layer with 207 input and 93 output channels with only a 2% latency overhead.

30 January 2020 in ACM Journal on Emerging Technologies in Computing Systems
Verified
Journal Article
Open access
Zhezhi HeZhezhi He
Zhezhi He
LYLi Yang
Li Yang
Shaahin AngiziShaahin Angizi
Shaahin Angizi
ARAdnan Siraj Rakin
Adnan Siraj Rakin
DFDeliang Fan
Deliang Fan
In this work, we propose a multiplication-less binarized depthwise-separable convolution neural network, called BD-Net. BD-Net is designed to use binarized depthwise separable convolution block as the drop-in replacement of conventional spatial-convolution in deep convolution neural network (DNN). In BD-Net, the computation-expensive convolution operations (i.e., Multiplication and Accumulation) are converted into energy-efficient Addition/Subtraction operations. For further compressing the model size while maintaining the dominant computation in addition/subtraction, we propose a brand-new sparse binarization method with a hardware-oriented structured sparsity pattern. To successfully train such sparse BD-Net, we propose and leverage two techniques: (1) a modified group-lasso regularization whose group size is identical to the capacity of basic computing core in accelerator and (2) a weight penalty clipping technique to solve the disharmony issue between weight binarization and lasso regularization. The experiment results show that the proposed sparse BD-Net can achieve comparable or even better inference accuracy, in comparison to the full precision CNN baseline. Beyond that, a BD-Net customized process-in-memory accelerator is designed using SOT-MRAM, which owns characteristics of high channel expansion flexibility and computation parallelism. Through the detailed analysis from both software and hardware perspectives, we provide an intuitive design guidance for software/hardware co-design of DNN acceleration on mobile embedded systems. Note that this journal submission is the extended version of our previous published paper in ISVLSI 2018 [24].

27 December 2021 in IEEE Design & Test
Verified
Journal Article
Closed access
SCSai Kiran Cherupally
Sai Kiran Cherupally
JMJian Meng
Jian Meng
ARAdnan Siraj Rakin
Adnan Siraj Rakin
SYShihui Yin
Shihui Yin
MSMingoo Seok
Mingoo Seok
JSJae-Sun Seo
Jae-Sun Seo
Like any other designs, in-memory computing (IMC) also suffers from operational inaccuracy induced by hardware noise. In this work, the authors propose to take into account hardware noises during the deep neural network (DNN) training in order to improve the DNN inference accuracy.


23 June 2024
Verified
Conference Paper
Open access
RZRanyang Zhou
Ranyang Zhou
SASabbir Ahmed
Sabbir Ahmed
ARAdnan Siraj Rakin
Adnan Siraj Rakin
Shaahin AngiziShaahin Angizi
Shaahin Angizi
With deep learning deployed in many security-sensitive areas, machine learning security is becoming progressively important. Recent studies demonstrate attackers can exploit system-level techniques exploiting the RowHammer vulnerability of DRAM to deterministically and precisely flip bits in Deep Neural Networks (DNN) model weights to affect inference accuracy. The existing defense mechanisms are software-based, such as weight reconstruction requiring expensive training overhead or performance degradation. On the other hand, generic hardware-based victim-/aggressor-focused mechanisms impose expensive hardware overheads and preserve the spatial connection between victim and aggressor rows. In this paper, we present the first DRAM-based victim-focused defense mechanism tailored for quantized DNNs, named DNN-Defender that leverages the potential of in-DRAM swapping to withstand the targeted bit-flip attacks with a priority protection mechanism. Our results indicate that DNN-Defender can deliver a high level of protection downgrading the performance of targeted RowHammer attacks to a random attack level. In addition, the proposed defense has no accuracy drop on CIFAR-10 and ImageNet datasets without requiring any software training or incurring hardware overhead.