A Resizing Method to Minimize Effects of Hardware Trojans

Cha, Byeongju; Gupta, Sandeep

doi:10.1109/ats.2014.44

Cited by 10 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MOLES [ 42 ] proposed the use of new payloads that could generate intentional side-channel signals to leak secret information. To evade detection, a circuit with gate resizing was redesigned at minimal cost without impacting the circuit’s functionality [ 43 ]. Zero overhead malicious modifications were proposed for high-performance and embedded microprocessors, where hardware Trojans were activated under specific conditions to obfuscate modifications [ 44 ].…”

Section: Related Work and Motivationmentioning

confidence: 99%

Hardware Trojan Attacks on the Reconfigurable Interconnections of Field-Programmable Gate Array-Based Convolutional Neural Network Accelerators and a Physically Unclonable Function-Based Countermeasure Detection Technique

Hou,

Liu,

Yang

et al. 2024

Micromachines

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have demonstrated significant superiority in modern artificial intelligence (AI) applications. To accelerate the inference process of CNNs, reconfigurable CNN accelerators that support diverse networks are widely employed for AI systems. Given the ubiquitous deployment of these AI systems, there is a growing concern regarding the security of CNN accelerators and the potential attacks they may face, including hardware Trojans. This paper proposes a hardware Trojan designed to attack a crucial component of FPGA-based CNN accelerators: the reconfigurable interconnection network. Specifically, the hardware Trojan alters the data paths during activation, resulting in incorrect connections in the arithmetic circuit and consequently causing erroneous convolutional computations. To address this issue, the paper introduces a novel detection technique based on physically unclonable functions (PUFs) to safeguard the reconfigurable interconnection network against hardware Trojan attacks. Experimental results demonstrate that by incorporating a mere 0.27% hardware overhead to the accelerator, the proposed hardware Trojan can degrade the inference accuracy of popular neural network architectures, including LeNet, AlexNet, and VGG, by a significant range of 8.93% to 86.20%. The implemented arbiter-PUF circuit on a Xilinx Zynq XC7Z100 platform successfully detects the presence and location of hardware Trojans in a reconfigurable interconnection network. This research highlights the vulnerability of reconfigurable CNN accelerators to hardware Trojan attacks and proposes a promising detection technique to mitigate potential security risks. The findings underscore the importance of addressing hardware security concerns in the design and deployment of AI systems utilizing FPGA-based CNN accelerators.

show abstract

Section: Related Work and Motivationmentioning

confidence: 99%

Hardware Trojan Attacks on the Reconfigurable Interconnections of Field-Programmable Gate Array-Based Convolutional Neural Network Accelerators and a Physically Unclonable Function-Based Countermeasure Detection Technique

Hou,

Liu,

Yang

et al. 2024

Micromachines

View full text Add to dashboard Cite

show abstract

“…The difficulty of detecting hardware trojans is determined by their triggers. Considerable research has been conducted on IC trojan design and the evaluation of new triggers [41][42][43][44]. However, much more research has been performed on the development of methodologies for countermeasures, which can be broadly classified as detection methods [39,[45][46][47][48], and prevention methods [49][50][51][52][53][54].…”

Section: Sensorsmentioning

confidence: 99%

Hardware-Based Methods for Electronic Device Protection against Invasive and Non-Invasive Attacks

Vidaković,

Vinko

2023

Electronics

View full text Add to dashboard Cite

This paper reviews hardware-based protection methods for electronic devices, encompassing scientific publications and published patents. This review covers insights from the scientific community and innovative solutions patented in the industry. By combining these two sources, this paper offers a comprehensive and holistic review of electronic device security. Electronic devices are integral to modern life, but their widespread use invites security threats, both digital and physical. This paper reviews hardware-based protection methods against invasive and non-invasive attacks, emphasizing the importance of a dual approach through hardware design. Invasive attacks involve physical tampering, and we explore anti-tampering techniques such as conductive meshes, sensors and physically unclonable functions (PUFs). Non-invasive, side-channel attacks encompass various attack vectors, focusing on electromagnetic analysis. To counter these attacks, we analyze techniques like reducing and masking electromagnetic radiation. This paper bridges the gap between invasive and non-invasive attack mitigation. It underscores the necessity of a multifaceted approach to safeguard electronic devices in an interconnected world, preserving their reliability and functionality.

show abstract

“…Designing and defending against HTs in a chip has been a hot research topic [2,3,4,1,5,6]. Various HTs and countermeasures have been proposed [2,7,8,9,10,11,12]. A typical HT is made of the trigger, the Trojan circuit and the payload [1].…”

Section: Hardware Trojansmentioning

confidence: 99%

Effectiveness of HT-assisted sinkhole and blackhole denial of service attacks targeting mesh networks-on-chip

Zhang

Wang

Jiang

et al. 2018

Journal of Systems Architecture

View full text Add to dashboard Cite

There are ample opportunities at both design and manufacturing phases to meddle in a many-core chip system, especially its underlining communication fabric, known as the networks-on-chip (NoC), through the inclusion of malicious hardware Trojans (HT). In this paper, we focus on studying two specific HT-assisted Denial-of-Service (DoS) attacks, namely the sinkhole and blackhole attacks, that directly target the NoC of a many-core chip. As of the blackhole attacks, those intermediate routers with inserted HTs can stop forwarding data packets/flits towards the packets' destination; instead, packets are either dropped from the network or diverted to some other malicious nodes. Sinkhole attacks, which exhibit similar attack effects as blackhole attacks, can occur when the NoC supports adaptive routing. In this case, a malicious node actively solicits packets from its neighbor nodes by pretending to have sufficient free buffer slots. Effects and efficiencies of both sinkhole and blackhole DoS attacks are modeled and quantified in this paper, and a few factors that influence attack effects are found to be critical. Through fine-tuning of these parameters, both attacks are shown to cause more damages to the NoC, measured as over 30% increase in packet loss rate. Even with current detection and defense methods in place, the packet loss rate is still remarkably high, suggesting the need of new and more effective detection and defense methods against the enhanced blackhole and sinkhole attacks as described in the paper.

show abstract

A Resizing Method to Minimize Effects of Hardware Trojans

Cited by 10 publications

References 24 publications

Hardware Trojan Attacks on the Reconfigurable Interconnections of Field-Programmable Gate Array-Based Convolutional Neural Network Accelerators and a Physically Unclonable Function-Based Countermeasure Detection Technique

Hardware Trojan Attacks on the Reconfigurable Interconnections of Field-Programmable Gate Array-Based Convolutional Neural Network Accelerators and a Physically Unclonable Function-Based Countermeasure Detection Technique

Hardware-Based Methods for Electronic Device Protection against Invasive and Non-Invasive Attacks

Effectiveness of HT-assisted sinkhole and blackhole denial of service attacks targeting mesh networks-on-chip

Contact Info

Product

Resources

About