Climbing Down the Hierarchy: Hierarchical Classification for Machine Learning Side-Channel Attacks

Picek, Stjepan; Heuser, Annelie; Jović, Alan; Legay, Axel

doi:10.1007/978-3-319-57339-7_4

Cited by 15 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that machine learning techniques could perform better than classical profiled side-channel attacks [13]. The researchers first started with simpler machine learning techniques like Random Forest and Support Vector Machines and targets without countermeasures [14], [15], [16], [17], [18]. Already these results suggested machine learning to be very powerful, especially in settings where the training phase was limited, i.e., the attacker had a relatively small number of measurements to profile.…”

Section: A Machine Learning-based Scamentioning

confidence: 99%

Mind the Portability: A Warriors Guide through Realistic Profiled Side-channel Analysis

Bhasin¹,

Chattopadhyay²,

Heuser³

et al. 2020

Proceedings 2020 Network and Distributed System Security Symposium

Self Cite

View full text Add to dashboard Cite

Profiled side-channel attacks represent a practical threat to digital devices, thereby having the potential to disrupt the foundation of e-commerce, the Internet of Things (IoT), and smart cities. In the profiled side-channel attack, the adversary gains knowledge about the target device by getting access to a cloned device. Though these two devices are different in realworld scenarios, yet, unfortunately, a large part of research works simplifies the setting by using only a single device for both profiling and attacking. There, the portability issue is conveniently ignored to ease the experimental procedure. In parallel to the above developments, machine learning techniques are used in recent literature, demonstrating excellent performance in profiled side-channel attacks. Again, unfortunately, the portability is neglected. In this paper, we consider realistic side-channel scenarios and commonly used machine learning techniques to evaluate the influence of portability on the efficacy of an attack. Our experimental results show that portability plays an important role and should not be disregarded as it contributes to a significant overestimate of the attack efficiency, which can easily be an order of magnitude size. After establishing the importance of portability, we propose a new model called the Multiple Device Model (MDM) that formally incorporates the device to device variation during a profiled side-channel attack. We show through experimental studies how machine learning and MDM significantly enhance the capacity for practical side-channel attacks. More precisely, we demonstrate how MDM can improve the performance of an attack by order of magnitude, completely negating the influence of portability.

show abstract

Section: A Machine Learning-based Scamentioning

confidence: 99%

Mind the Portability: A Warriors Guide through Realistic Profiled Side-channel Analysis

Bhasin¹,

Chattopadhyay²,

Heuser³

et al. 2020

Proceedings 2020 Network and Distributed System Security Symposium

Self Cite

View full text Add to dashboard Cite

show abstract

“…Picek et al presented an approach called hierarchical classification [99]. The idea is to explore the natural clustering of the leakage in order to arrange the sensitive variables in a tree structure.…”

Section: Ml-based Side-channel Analysis Of Hardware Vulnerabilitiesmentioning

confidence: 99%

A Survey on Hardware Vulnerability Analysis Using Machine Learning

Pan

Mishra

2022

IEEE Access

View full text Add to dashboard Cite

Electronic systems rely on efficient hardware, popularly known as system-on-chip (SoC), to support its core functionalities. A typical SoC consists of diverse components gathered from third-party vendors to reduce SoC design cost and meet time-to-market constraints. Unfortunately, the participation of third-party companies in global supply chain introduces potential security vulnerabilities. There is a critical need to efficiently detect and mitigate hardware vulnerabilities. Machine learning has been successfully used in hardware security verification as well as development of effective countermeasures. There are recent surveys on hardware Trojan detection using machine learning. To the best of our knowledge, there are no comprehensive surveys on utilization of machine learning techniques for detection and mitigation of a wide variety of hardware vulnerabilities including malicious implants (e.g., hardware Trojans), sidechannel leakage, reverse engineering, and supply-chain vulnerabilities (e.g., counterfeiting, overbuilding and recycling). In this paper, we provide a comprehensive survey of hardware vulnerability analysis using machine learning techniques. Specifically, we discuss how existing approaches effectively utilize machine learning algorithms for hardware security verification using simulation-based validation, formal verification as well as side-channel analysis.

show abstract

“…For example, if it is known that the power consumption is correlated with the HW of data, then the training labels would be the HW of the intermediate variable. Classical machine learning techniques use a leakage model for classification [35], [36]. Further, these techniques usually require a dimension reduction algorithm, such as principal component analysis (PCA), to select points of interest (POI) of power traces [25].…”

Section: Supervised Learning Attacksmentioning

confidence: 99%

SCAUL: Power Side-Channel Analysis with Unsupervised Learning

Ramezanpour¹,

Ampadu²,

Diehl³

2020

Preprint

View full text Add to dashboard Cite

Existing power analysis techniques rely on strong adversary models with prior knowledge of the leakage or training data. We introduce side-channel analysis with unsupervised learning (SCAUL) that can recover the secret key without requiring prior knowledge or profiling (training). We employ an LSTM auto-encoder to extract features from power traces with high mutual information with the data-dependent samples of the measurements. We demonstrate that by replacing the raw measurements with the auto-encoder features in a classical DPA attack, the efficiency, in terms of required number of measurements for key recovery, improves by 10X. Further, we employ these features to identify a leakage model with sensitivity analysis and multi-layer perceptron (MLP) networks. SCAUL uses the auto-encoder features and the leakage model, obtained in an unsupervised approach, to find the correct key. On a lightweight implementation of AES on Artix-7 FPGA, we show that SCAUL is able to recover the correct key with 3700 power measurements with random plaintexts, while a DPA attack requires at least 17400 measurements. Using misaligned traces, with an uncertainty equal to 20% of the hardware clock cycle, SCAUL is able to recover the secret key with 12300 measurements while the DPA attack fails to detect the key.

show abstract

Climbing Down the Hierarchy: Hierarchical Classification for Machine Learning Side-Channel Attacks

Cited by 15 publications

References 17 publications

Mind the Portability: A Warriors Guide through Realistic Profiled Side-channel Analysis

Mind the Portability: A Warriors Guide through Realistic Profiled Side-channel Analysis

A Survey on Hardware Vulnerability Analysis Using Machine Learning

SCAUL: Power Side-Channel Analysis with Unsupervised Learning

Contact Info

Product

Resources

About