SK
S. Karayalçin
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Some of the most prominent types of attacks against modern cryptographic implementations are side-channel attacks. These attacks leverage some unintended, often physical, leakage of the implementation to retrieve secret information. In recent times, a large part of the focus of side-channel research has been on deep learning methods. These methods operate in a profiled setting where a model is learned based on a copy of the device that is being attacked. This model is subsequently used to create significantly more potent attacks against the target. Attacks using deep learning methods can often defeat even implementations protected with countermeasures, but as implementations become more protected, novel methods are required to successfully generate attacks.
Recently, residual neural networks have been used for side-channel attacks, and these networks show promising attacking performance. However, these novel networks are relatively limited, and a more thorough investigation into the construction of residual networks in the side-channel context is required.
Our contribution is a more thorough investigation into the construction of these residual architectures. We explore several important factors to the construction of these models and generate insights into various methods for this construction. The resulting architectures we find show attacking performance that is competitive with the state-of-the-art methods across various data sets and feature selection scenarios. ...
Recently, residual neural networks have been used for side-channel attacks, and these networks show promising attacking performance. However, these novel networks are relatively limited, and a more thorough investigation into the construction of residual networks in the side-channel context is required.
Our contribution is a more thorough investigation into the construction of these residual architectures. We explore several important factors to the construction of these models and generate insights into various methods for this construction. The resulting architectures we find show attacking performance that is competitive with the state-of-the-art methods across various data sets and feature selection scenarios. ...
Some of the most prominent types of attacks against modern cryptographic implementations are side-channel attacks. These attacks leverage some unintended, often physical, leakage of the implementation to retrieve secret information. In recent times, a large part of the focus of side-channel research has been on deep learning methods. These methods operate in a profiled setting where a model is learned based on a copy of the device that is being attacked. This model is subsequently used to create significantly more potent attacks against the target. Attacks using deep learning methods can often defeat even implementations protected with countermeasures, but as implementations become more protected, novel methods are required to successfully generate attacks.
Recently, residual neural networks have been used for side-channel attacks, and these networks show promising attacking performance. However, these novel networks are relatively limited, and a more thorough investigation into the construction of residual networks in the side-channel context is required.
Our contribution is a more thorough investigation into the construction of these residual architectures. We explore several important factors to the construction of these models and generate insights into various methods for this construction. The resulting architectures we find show attacking performance that is competitive with the state-of-the-art methods across various data sets and feature selection scenarios.
Recently, residual neural networks have been used for side-channel attacks, and these networks show promising attacking performance. However, these novel networks are relatively limited, and a more thorough investigation into the construction of residual networks in the side-channel context is required.
Our contribution is a more thorough investigation into the construction of these residual architectures. We explore several important factors to the construction of these models and generate insights into various methods for this construction. The resulting architectures we find show attacking performance that is competitive with the state-of-the-art methods across various data sets and feature selection scenarios.
Bachelor thesis
(2020)
-
Sengim Karayalçin, Stefanie Roos, Satwik Prabhu Kumble, Ranga Rao Venkatesha Prasad
Blockchains and cryptocurrencies, like Ripple, are becoming more widely used. Testing the large decentralized systems these technologies on is complex, as the behavior of the system is dependent on many external factors. We will examine the viability of using passive model inference techniques to test the systems based on the network traffic they produce. Passive inference techniques have been used extensively to model and test different types of systems. However, it is unclear how well passive model inference techniques work for inferring models of large decentralized systems based on the network traffic that these systems produce. Here we show that detecting bugs in the implementations of decentralized protocols is possible. These results were achieved by simulating a version of the Ripple network and modeling the workings of a node in this network. We also simulated the network with defective nodes and by observing the different models generated, were able to detect these bugs. Our results suggest that using passive model inference techniques on network traffic can help test large decentralized systems.
...
Blockchains and cryptocurrencies, like Ripple, are becoming more widely used. Testing the large decentralized systems these technologies on is complex, as the behavior of the system is dependent on many external factors. We will examine the viability of using passive model inference techniques to test the systems based on the network traffic they produce. Passive inference techniques have been used extensively to model and test different types of systems. However, it is unclear how well passive model inference techniques work for inferring models of large decentralized systems based on the network traffic that these systems produce. Here we show that detecting bugs in the implementations of decentralized protocols is possible. These results were achieved by simulating a version of the Ripple network and modeling the workings of a node in this network. We also simulated the network with defective nodes and by observing the different models generated, were able to detect these bugs. Our results suggest that using passive model inference techniques on network traffic can help test large decentralized systems.