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

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.

A Circuit-Level Solution for Secure Temperature Sensor

Temperature sensors play an important role in modern monitoring and control applications. When more and more sensors are integrated into internet-connected systems, the integrity and security of sensors become a concern and cannot be ignored anymore. As sensors are typically low-end devices, there is no built-in defense mechanism in sensors. It is common that system-level defense provides protection against security threats on sensors. Unfortunately, high-level countermeasures do not differentiate the root of cause and treat all anomalies with system-level recovery processes, resulting in high-cost overhead on delay and power consumption. In this work, we propose a secure architecture for temperature sensors with a transducer and a signal conditioning unit. The proposed architecture estimates the sensor data with statistical analysis and generates a residual signal for anomaly detection at the signal conditioning unit. Moreover, complementary current-temperature characteristics are exploited to generate a constant current reference for attack detection at the transducer level. Anomaly detection at the signal conditioning unit and attack detection at the transducer unit make the temperature sensor attack resilient to intentional and unintentional attacks. Simulation results show that our sensor is capable of detecting an under-powering attack and analog Trojan from a significant signal vibration in the constant current reference. Furthermore, the anomaly detection unit detects anomalies at the signal conditioning level from the generated residual signal. The proposed detection system is resilient against any intentional and unintentional attacks, with a detection rate of 97.73%.

A Cost-Driven Method for Deep-Learning-Based Hardware Trojan Detection

The Cyber-Physical System and even the Metaverse will become the second space in which human beings live. While bringing convenience to human beings, it also brings many security threats. These threats may come from software or hardware. There has been a lot of research on managing malware, and there are many mature commercial products, such as antivirus software, firewalls, etc. In stark contrast, the research community on governing malicious hardware is still in its infancy. Chips are the core component of hardware, and hardware Trojans are the primary and complex security issue faced by chips. Detection of hardware Trojans is the first step for dealing with malicious circuits. Due to the limitation of the golden chip and the computational consumption, the existing traditional detection methods are not applicable to very large-scale integration. The performances of traditional machine-learning-based methods depend on the accuracy of the multi-feature representation, and most of the methods may lead to instability because of the difficulty of extracting features manually. In this paper, employing deep learning, a multiscale detection model for automatic feature extraction is proposed. The model is called MHTtext and provides two strategies to balance the accuracy and computational consumption. After selecting a strategy according to the actual situations and requirements, the MHTtext generates the corresponding path sentences from the netlist and employs TextCNN for identification. Further, it can also obtain non-repeated hardware Trojan component information to improve its stability performance. Moreover, a new evaluation metric is established to intuitively measure the model's effectiveness and balance: the stabilization efficiency index (SEI). In the experimental results for the benchmark netlists, the average accuracy (ACC) in the TextCNN of the global strategy is as high as 99.26%, and one of its stabilization efficiency index values ranks first with a score of 71.21 in all comparison classifiers. The local strategy also achieved an excellent effect, according to the SEI. The results show that the proposed MHTtext model has high stability, flexibility, and accuracy, in general.