Invasive Attacks

Tria, Assia; Choukri, Hamid

doi:10.1007/0-387-23483-7_205

Cited by 5 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main difference between the non-invasive and invasive attacks is in the approach of attacking the TOEs. To perform an invasive attack, it is required to remove at least part of the passivation layer to establish the contact between the probes and silicon [16]. Non-invasive attacks, on the other hand, mainly focus on investigating the settings that can be controlled externally [17], or passively measuring the running time, the cache behavior, the power consumption, and/or the electromagnetic radiation of the device through the package [18].…”

Section: Fault Injection Attacksmentioning

confidence: 99%

A Fast Characterization Method for Semi-invasive Fault Injection Attacks

Ribera²,

Beringuier-Boher³

et al. 2020

Topics in Cryptology – CT-RSA 2020

View full text Add to dashboard Cite

Semi-invasive fault injection attacks are powerful techniques well-known by attackers and secure embedded system designers. When performing such attacks, the selection of the fault injection parameters is of utmost importance and usually based on the experience of the attacker. Surprisingly, there exists no formal and general approach to characterize the target behavior under attack. In this work, we present a novel methodology to perform a fast characterization of the fault injection impact on a target, depending on the possible attack parameters. We experimentally show our methodology to be a successful one when targeting different algorithms such as DES and AES encryption and then extend to the full characterization with the help of deep learning. Finally, we show how the characterization results are transferable between different targets.

show abstract

Section: Fault Injection Attacksmentioning

confidence: 99%

A Fast Characterization Method for Semi-invasive Fault Injection Attacks

Ribera²,

Beringuier-Boher³

et al. 2020

Topics in Cryptology – CT-RSA 2020

View full text Add to dashboard Cite

show abstract

“…Finally, invasive attacks access the internals of a chip. These include approaches such as decapsulation (a procedure where the chip packaging is removed), microprobing (where the attacker can probe the internals of a chip), chemical attacks that can reveal information stored in read-only memory, and scanning electron microscope (SEM) attacks (which are able to read RAM memory) [27]. These attacks typically require specialized labs and expensive equipment.…”

Section: Attacker's Level Of Accessmentioning

confidence: 99%

“…Both these works show that, despite the robustness of neural networks to random perturbations, networks are highly susceptible to targeted bit-flips, in a manner similar to non-targeted adversarial attacks [58]. While we have not been able to find any examples of this, we expect neural network accelerators to be vulnerable to cold boot attacks [59], which may be able to steal unencrypted models stored in volatile memory, or microprobing [27], which may be able to bypass model or user data decryption.…”

Section: Attacks On Deployed Neural Networkmentioning

confidence: 99%

Survey of Attacks and Defenses on Edge-Deployed Neural Networks

Isakov¹,

Gadepally

Gettings

et al. 2019

2019 IEEE High Performance Extreme Computing Conference (HPEC)

View full text Add to dashboard Cite

Deep Neural Network (DNN) workloads are quickly moving from datacenters onto edge devices, for latency, privacy, or energy reasons. While datacenter networks can be protected using conventional cybersecurity measures, edge neural networks bring a host of new security challenges. Unlike classic IoT applications, edge neural networks are typically very compute and memory intensive, their execution is data-independent, and they are robust to noise and faults. Neural network models may be very expensive to develop, and can potentially reveal information about the private data they were trained on, requiring special care in distribution. The hidden states and outputs of the network can also be used in reconstructing user inputs, potentially violating users' privacy. Furthermore, neural networks are vulnerable to adversarial attacks, which may cause misclassifications and violate the integrity of the output. These properties add challenges when securing edge-deployed DNNs, requiring new considerations, threat models, priorities, and approaches in securely and privately deploying DNNs to the edge. In this work, we cover the landscape of attacks on, and defenses, of neural networks deployed in edge devices and provide a taxonomy of attacks and defenses targeting edge DNNs.

show abstract

“…The value of this equipment may far exceed the value of the targets being attacked. The attack process is also complicated, and even an experienced attacker may take several months, resulting in higher attack costs [31]. Therefore, attacks such as physical side-channel attacks, code injection attacks, and other complex physical attacks are out of the scope of our research.…”

Section: Threat Modelmentioning

confidence: 99%

SoftME: A Software-Based Memory Protection Approach for TEE System to Resist Physical Attacks

Zhang

Zhao

et al. 2019

Security and Communication Networks

View full text Add to dashboard Cite

The development of the Internet of Things has made embedded devices widely used. Embedded devices are often used to process sensitive data, making them the target of attackers. ARM TrustZone technology is used to protect embedded device data from compromised operating systems and applications. But as the value of the data stored in embedded devices increases, more and more effective physical attacks have emerged. However, TrustZone cannot resist physical attacks. We propose SoftME, an approach that utilizes the on-chip memory space to provide a trusted execution environment for sensitive applications. We protect the confidentiality and integrity of the data stored on the off-chip memory. In addition, we design task scheduling in the encryption process. We implement a prototype system of our approach on the development board supporting TrustZone and evaluate the overhead of our approach. The experimental results show that our approach improves the security of the system, and there is no significant increase in system overhead.

show abstract

Invasive Attacks

Cited by 5 publications

References 0 publications

A Fast Characterization Method for Semi-invasive Fault Injection Attacks

A Fast Characterization Method for Semi-invasive Fault Injection Attacks

Survey of Attacks and Defenses on Edge-Deployed Neural Networks

SoftME: A Software-Based Memory Protection Approach for TEE System to Resist Physical Attacks

Contact Info

Product

Resources

About