Fault attack is a class of active implementation based attacks which introduces controlled pertur... more Fault attack is a class of active implementation based attacks which introduces controlled perturbations in the normal operation of a system to produce faulty outcomes. In case of ciphers, these faulty outcomes can lead to leakage of secret information, such as the secret key. The effectiveness and practicality of fault attacks largely depend on the underlying fault model and the type of fault induced. In this paper, we analyse the drawbacks of persistent fault model in case of error correction code (ECC) enabled systems. We further propose a novel fault attack called Intermittent Fault Attack which is well suited for ECC-enabled DRAM modules. We demonstrate the practicality of our attack model by inducing single bit faults using pinpointed Rowhammer technique in S-Boxes of block ciphers in a ECC protected system.
Deep learning has emerged as a strong and efficient framework that can be applied to a broad spec... more Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few years, deep learning has advanced radically in such a way that it can surpass human-level performance on a number of tasks. As a consequence, deep learning is being extensively used in most of the recent day-to-day applications. However, security of deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify the output. In recent times, different types of adversaries based on their threat model leverage these vulnerabilities to compromise a deep learning system where adversaries have high incentives. Hence, it is extremely important to provide robustness to deep learning algorithms against these adversaries. However, there are only a few strong countermeas...
Fault attack is a class of active implementation based attacks which introduces controlled pertur... more Fault attack is a class of active implementation based attacks which introduces controlled perturbations in the normal operation of a system to produce faulty outcomes. In case of ciphers, these faulty outcomes can lead to leakage of secret information, such as the secret key. The effectiveness and practicality of fault attacks largely depend on the underlying fault model and the type of fault induced. In this paper, we analyse the drawbacks of persistent fault model in case of error correction code (ECC) enabled systems. We further propose a novel fault attack called Intermittent Fault Attack which is well suited for ECC-enabled DRAM modules. We demonstrate the practicality of our attack model by inducing single bit faults using pinpointed Rowhammer technique in S-Boxes of block ciphers in a ECC protected system.
Deep learning has emerged as a strong and efficient framework that can be applied to a broad spec... more Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few years, deep learning has advanced radically in such a way that it can surpass human-level performance on a number of tasks. As a consequence, deep learning is being extensively used in most of the recent day-to-day applications. However, security of deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify the output. In recent times, different types of adversaries based on their threat model leverage these vulnerabilities to compromise a deep learning system where adversaries have high incentives. Hence, it is extremely important to provide robustness to deep learning algorithms against these adversaries. However, there are only a few strong countermeas...
Uploads
Papers by Anirban Chakraborty