Side-channel attacks and machine learning approach

Levina, Alla; Sleptsova, Daria; Зайцев, О. В.

doi:10.1109/fruct-ispit.2016.7561525

Cited by 9 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acoustic side-channel attacks eavesdrop on sound artifacts produced by a system using covert listening devices (Levina, Sleptsova and Zaitsev, 2016). Acoustic signals may be generated through user operation, such as clicks resulting from keypad inputs.…”

Section: Side-channel Attacksmentioning

confidence: 99%

An Introduction to Semantic Threat Analysis for Systems Security Engineering

Potember

Balhana

Obrst

2022

INCOSE International Symp

View full text Add to dashboard Cite

The objectives of this paper are (a) to motivate the adoption of semantic graphical models of threat relations and countermeasures in the design and operation of cyber‐physical systems (CPS), and (b) to raise awareness of the various benefits which systems security engineers (SSEs) stand to gain by adopting such practices. Specifically, we propose that a Semantic Threat Analysis (STA) can endow SSEs with a comprehensive, extensible, machine‐readable, and logically inferable model of system features. An STA shaped to the specific architecture and security requirements of a CPS environment can support the identification and visualization of system interdependencies and process flows among network, computing, mechanical, security, and access control components. The proposed STA process presupposes a team‐oriented systems engineering approach employing a combination of subject matter experts (SMEs) and ontologists who can bring their respective expertise together to bear on the task.

show abstract

Section: Side-channel Attacksmentioning

confidence: 99%

An Introduction to Semantic Threat Analysis for Systems Security Engineering

Potember

Balhana

Obrst

2022

INCOSE International Symp

View full text Add to dashboard Cite

show abstract

“…In Reference 36, Prouff et al have used ML‐SCA to recover the secret key by using the hamming weight strategy for class labeling. In Reference 37, Levina et al have discussed the applicability of the machine‐learning methods for secret key classification tasks, based on the bitwise and byte‐wise analysis. Furthermore, Cagli et al and Kim et al have presented early studies which show that deep learning outperforms the traditional side‐channel analysis methods, since they have the capability of learning from the misaligned countermeasure protected data as well 17,20 .…”

Section: Background and Related Workmentioning

confidence: 99%

“…As the side‐channel attacks exploit the relationship dependency of the leakage data with the processed secret data/key, hence, the same leakage trace might represent a single key bit, a key nibble, a key byte, or a particular algorithm operation (e.g., addition or doubling). The resulting design model leads to binary or multiclass classification problems, as has been presented in literature 35‐37 . The hamming weight‐based class labeling model is the most popular model for analyzing cryptographic algorithms.…”

Section: Deep‐learning Based Side‐channel Analysis Systemmentioning

confidence: 99%

“…The resulting design model leads to binary or multiclass classification problems, as has been presented in literature. [35][36][37] The hamming weight-based class labeling model is the most popular model for analyzing cryptographic algorithms. The majority of these machine-learning-based side-channel analysis (SCA) models are presented for symmetric key algorithms.…”

Section: Attack Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Edge enhanced deep learning system for IoT edge device security analytics

Mukhtar

Mehrabi

Kong

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

The processing of locally harvested data at the physically accessible edge devices opens a new avenue of security threats for edge enhanced analytics. Cryptographic algorithms are used to secure the data being processed on the edge device. However, the implementation weakness of the algorithms on the edge devices can lead to side‐channel attack vulnerability, which is exacerbated with the application of machine‐learning techniques. This research proposes a deep learning‐based system integrated at the edge device to identify the side‐channel leakages. To design such a deep learning‐based system, one of the challenges is formulating the suitable attack model for the underlying target algorithm. Based on the previous findings, three machine learning‐based side‐channel attack models are curated and investigated for the edge device security evaluations. As a test case, the standard elliptic‐curve cryptographic algorithm is selected. Moreover, quantitative analysis is provided for the best attack model selection using standard machine‐learning evaluation metrics. A comparative analysis is performed on the raw unaligned data samples and reduced feature‐engineered samples using edge enhanced security analytics. The investigation concludes that the vulnerable algorithm implementation can lead to the secret key recovery from the edge device, with 96% accuracy, using a neural‐network‐based algorithm to analyse side‐channel attacks.

show abstract

“…Recently, researchers have performed machine-learning and neural-network-based analysis to improve side-channel attack efficiency, using various classifiers, to recover the key from the DES, AES and RSA hardware implementations [19][20][21][22][23]. Some of the major challenges of machine learning are over-fitting and the curse of dimensionality, in which a model trains itself to the specific data so well that it fails to predict accurately with new unseen data.…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning-Based Side-Channel Evaluation of Elliptic-Curve Cryptographic FPGA Processor

et al. 2018

View full text Add to dashboard Cite

Security of embedded systems is the need of the hour. A mathematically secure algorithm runs on a cryptographic chip on these systems, but secret private data can be at risk due to side-channel leakage information. This research focuses on retrieving secret-key information, by performing machine-learning-based analysis on leaked power-consumption signals, from Field Programmable Gate Array (FPGA) implementation of the elliptic-curve algorithm captured from a Kintex-7 FPGA chip while the elliptic-curve cryptography (ECC) algorithm is running on it. This paper formalizes the methodology for preparing an input dataset for further analysis using machine-learning-based techniques to classify the secret-key bits. Research results reveal how pre-processing filters improve the classification accuracy in certain cases, and show how various signal properties can provide accurate secret classification with a smaller feature dataset. The results further show the parameter tuning and the amount of time required for building the machine-learning models.

show abstract

Side-channel attacks and machine learning approach

Cited by 9 publications

References 14 publications

An Introduction to Semantic Threat Analysis for Systems Security Engineering

An Introduction to Semantic Threat Analysis for Systems Security Engineering

Edge enhanced deep learning system for IoT edge device security analytics

Machine-Learning-Based Side-Channel Evaluation of Elliptic-Curve Cryptographic FPGA Processor

Contact Info

Product

Resources

About