相关论文: RF-Trojan: Leaking Kernel Data Using Register File…

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively…

We introduce a new class of hardware trojans called interrupt-resilient trojans (IRTs). Our work is motivated by the observation that hardware trojan attacks on CPUs, even under favorable attack scenarios (e.g., an attacker with local…

The growing complexity of global supply chains has made hardware Trojans a significant threat in sensor-based power electronics. Traditional Trojan designs depend on digital triggers or fixed threshold conditions that can be detected during…

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

As process technology scales down to smaller dimensions, DRAM chips become more vulnerable to disturbance, a phenomenon in which different DRAM cells interfere with each other's operation. For the first time in academic literature, our ISCA…

This paper discusses the possible introduction of hidden reliability defects during CMOS foundry fabrication processes that may lead to accelerated wearout of the devices. These hidden defects or hardware Trojans can be created by deviation…

Quantum computing has demonstrated superior efficiency compared to classical computing. Quantum circuits are essential for implementing functions and achieving correct computational outcomes. Quantum circuit compilers, which translate…

We will discuss the RowHammer problem in DRAM, which is a prime (and likely the first) example of how a circuit-level failure mechanism in Dynamic Random Access Memory (DRAM) can cause a practical and widespread system security…

Like all software systems, the execution of deep learning models is dictated in part by logic represented as data in memory. For decades, attackers have exploited traditional software programs by manipulating this data. We propose a live…

A recent trojan attack on deep neural network (DNN) models is one insidious variant of data poisoning attacks. Trojan attacks exploit an effective backdoor created in a DNN model by leveraging the difficulty in interpretability of the…

Trojan attacks on deep neural networks are both dangerous and surreptitious. Over the past few years, Trojan attacks have advanced from using only a single input-agnostic trigger and targeting only one class to using multiple,…

The implementation of cryptographic primitives in integrated circuits (ICs) continues to increase over the years due to the recent advancement of semiconductor manufacturing and reduction of cost per transistors. The hardware implementation…

This paper utilizes Reinforcement Learning (RL) as a means to automate the Hardware Trojan (HT) insertion process to eliminate the inherent human biases that limit the development of robust HT detection methods. An RL agent explores the…

Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the problem of Trojan…

There are increasing concerns about possible malicious modifications of integrated circuits (ICs) used in critical applications. Such attacks are often referred to as hardware Trojans. While many techniques focus on hardware Trojan…

The proficiency of Large Language Models (LLMs) in processing structured data and adhering to syntactic rules is a capability that drives their widespread adoption but also makes them paradoxically vulnerable. In this paper, we investigate…

Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory tracking and pose stabilization. However, their reliance on potentially untrusted training pipelines or supply chains introduces…

Graphic Processing Units (GPUs) have transcended their traditional use-case of rendering graphics and nowadays also serve as a powerful platform for accelerating ubiquitous, non-graphical rendering tasks. One prominent task is inference of…

Current Hardware Trojan (HT) detection techniques are mostly developed based on a limited set of HT benchmarks. Existing HT benchmark circuits are generated with multiple shortcomings, i.e., i) they are heavily biased by the designers'…

As part of the revelations about the NSA activities, the notion of interdiction has become known to the public: the interception of deliveries to manipulate hardware in a way that backdoors are introduced. Manipulations can occur on the…