A Review and Comparison of AI-enhanced Side Channel Analysis

Panoff, Max; Yu, Honggang; Shan, Haoqi; Jin, Yier

doi:10.1145/3517810

Cited by 14 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Panoff et al [6] presented a great deal of their research to study CNNs and other deep learning approaches for side-channel analysis. For the purpose of practicing sidechannel attacks, a variety of network setups and training methodologies were used.…”

Section: Literature Reviewmentioning

confidence: 99%

“…To address misaligned trace sets, the second method suggested in SCA literature is to do realignment preprocessing before to the assault. It is possible to classify realignment approaches into two groups: one focused on signal processing (see, for example, [5]) and better suited to hardware countermeasures; and another, more probabilistic in nature (see, for example, [6]), designed for detecting fake operations (software countermeasures).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design of Time-Delay Convolutional Neural Networks(TDCNN) Model for Feature Extraction for Side-Channel Attacks

Abbas Ahmed,

Kamrul Hasan,

Azman Mohd Noah

et al. 2024

IJCDS

View full text Add to dashboard Cite

This work explores a novel method of SCA profiling to address compatibility problems and strengthen Deep Learning (DL) models. Convolutional Neural Networks are proposed in this research as a countermeasure to misalignment-focused countermeasures. "Time-Delay Convolutional Neural Networks" (TDCNN) is more accurate than "Convolutional Neural Network," yet it's still acceptable. It's true that TDCNNs are neural networks based on convolution learned on single spatial information, just as side-channel tracings. However, given to recent surge in popularity of CNNs, particularly from the year 2012 when CNN framework ("AlexNet") achieved Image Net Large Scale Visual Recognition Competition which is a notable image detection competition, a novel TDCNN has been termed out in DL literature. Currently, it needs to employ the characteristics related to CNN design, including declaring that one input feature equals 1 for instance, to establish a TDCNN in the most widely used DL libraries.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Design of Time-Delay Convolutional Neural Networks(TDCNN) Model for Feature Extraction for Side-Channel Attacks

Abbas Ahmed,

Kamrul Hasan,

Azman Mohd Noah

et al. 2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…Without the need to preprocess the input, Cagli et al [29] found that an attacker utilizing convolutional neural networks could potentially recover the secret key using side-channel attacks based on deep learning key. The results of deep learning investigations can be compared with one another with the use of open datasets [30]. In order to break public-key cryptosystems [31], researchers have employed deep learning in tandem with block ciphers.…”

Section: Literature Reviewmentioning

confidence: 99%

Adaptive Optimization of Deep Learning Models on AES based Large Side Channel Attack Data

Muhammad,

Alzuabidi,

Ahmed

et al. 2024

KJCS

View full text Add to dashboard Cite

Deep learning-based side-channel analysis is an efficient and suitable technique for profiling side-channel attacks. In order to obtain the better performance, it is highly necessary to analyze an in-depth training stage in which the optimization of relevant hyperparameters should be a vital process. During the training phase, hyperparameters that are connected to the architecture of the neural network are often selected; however, hyperparameters that impact the training process are to be effectively analyzed. This was represented by an optimized hyperparammeter that consists of considerable impact on attacking behaviour, which is the primary focus of our research. Our research has shown that even while the popular optimizers Adam and RMSprop are capable of delivering satisfactory outcomes, they are also tend to being overfit. Hence, it is necessary to use condensed training periods, simple profiling models, and explicit regularization in order to avoid this problem. On the other hand, the performance of optimizers of the SGD type is only satisfactory when momentum is used which results in slower convergence and less overfit. In conclusion, the research results provide a better use of Adagrad in the cases of longer training datasets or big profiling models.

show abstract

“…Profiled side-channel analysis has posed a significant threat to embedded devices [12][13][14]. It aims to exploit various physical side-channel leakages such as power consumption or electromagnetic (EM) emanations to reveal confidential information (e.g., secret keys) from victim cryptographic algorithms.…”

Section: Profiled Side-channel Attackmentioning

confidence: 99%

Noise2Clean: Cross-Device Side-Channel Traces Denoising with Unsupervised Deep Learning

Wang

Song

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

Deep learning (DL)-based side-channel analysis (SCA) has posed a severe challenge to the security and privacy of embedded devices. During its execution, an attacker exploits physical SCA leakages collected from profiling devices to create a DL model for recovering secret information from victim devices. Despite this success, recent works have demonstrated that certain countermeasures, such as random delay interrupts or clock jitters, would make these attacks more complex and less practical in real-world scenarios. To address this challenge, we present a novel denoising scheme that exploits the U-Net model to pre-process SCA traces for “noises” (i.e., countermeasures) removal. Specifically, we first pre-train the U-Net model on the paired noisy-clean profiling traces to obtain suitable parameters. This model is then fine-tuned on the noisy-only traces collected from the attacking device. The well-trained model will be finally deployed on the attacking device to remove the noises (i.e., countermeasures) from the measured power traces. In particular, a new inductive transfer learning method is also utilized in our scheme to transfer knowledge learned from the source domain (i.e., profiling device) to the target domain (i.e., attacking device) to improve the model’s generalization ability. During our experimental evaluations, we conduct a detailed analysis of various countermeasures separately or combined and show that the proposed denoising model outperforms current state-of-the-art work by a large margin, e.g., a reduction of at least 30% in computation costs and 5× in guessing entropy.

show abstract

A Review and Comparison of AI-enhanced Side Channel Analysis

Cited by 14 publications

References 55 publications

Design of Time-Delay Convolutional Neural Networks(TDCNN) Model for Feature Extraction for Side-Channel Attacks

Design of Time-Delay Convolutional Neural Networks(TDCNN) Model for Feature Extraction for Side-Channel Attacks

Adaptive Optimization of Deep Learning Models on AES based Large Side Channel Attack Data

Noise2Clean: Cross-Device Side-Channel Traces Denoising with Unsupervised Deep Learning

Contact Info

Product

Resources

About