Black-Hat High-Level Synthesis: Myth or Reality?

Pilato, Christian; Basu, Kanad; Regazzoni, Francesco; Karri, Ramesh

doi:10.1109/tvlsi.2018.2884742

Cited by 19 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An attacker can utilize malicious processors to violate operating system exceptions and modify the open-source processor to create a malicious firmware [71]. Prior works have also demonstrated that Trojans can be introduced during EDA design flow and high-level synthesis [72], [73]. Additionally, Trojan can be activated under unexpected conditions or by silicon wear-out [74], [75].…”

Section: Machine Learning For Hardware Securitymentioning

confidence: 99%

Two Sides of the Same Coin: Boons and Banes of Machine Learning in Hardware Security

Liu

Chang

Wang

et al. 2021

IEEE J. Emerg. Sel. Topics Circuits Syst.

Self Cite

View full text Add to dashboard Cite

The last decade has witnessed remarkable research advances at the intersection of machine learning (ML) and hardware security. The confluence of the two technologies has created many interesting and unique opportunities, but also left some issues in their wake. ML schemes have been extensively used to enhance the security and trust of embedded systems like hardware Trojans and malware detection. On the other hand, ML-based approaches have also been adopted by adversaries to assist side-channel attacks, reverse engineer integrated circuits and break hardware security primitives like Physically Unclonable Functions (PUFs). Deep learning is a subfield of ML. It can continuously learn from a large amount of labeled data with a layered structure. Despite the impressive outcomes demonstrated by deep learning in many application scenarios, the dark side of it has not been fully exposed yet. The inability to fully understand and explain what has been done within the super-intelligence can turn an inherently benevolent system into malevolent. Recent research has revealed that the outputs of Deep Neural Networks (DNNs) can be easily corrupted by imperceptibly small input perturbations. As computations are brought nearer to the source of data creation, the attack surface of DNN has also been extended from the input data to the edge devices. Accordingly, due to the opportunities of MLassisted security and the vulnerabilities of ML implementation, in this paper, we will survey the applications, vulnerabilities and fortification of ML from the perspective of hardware security. We will discuss the possible future research directions, and thereby, sharing a roadmap for the hardware security community in general.

show abstract

Section: Machine Learning For Hardware Securitymentioning

confidence: 99%

Two Sides of the Same Coin: Boons and Banes of Machine Learning in Hardware Security

Liu

Chang

Wang

et al. 2021

IEEE J. Emerg. Sel. Topics Circuits Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Semiconductor companies commonly use third party EDA tools, third party IPs (3PIPs), and untrusted foundries. Insertion of Trojans during EDA design flow and high-level synthesis has been both demonstrated by [11], [12]. Malicious processors can be designed to allow users to violate Operating System exceptions and operate on a malicious firmware by modifying the open source processor [13].…”

Section: Background a Hardware Trojansmentioning

confidence: 99%

Can Overclocking Detect Hardware Trojans?

Meng

Hassan

Dinakrrao

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

Self Cite

View full text Add to dashboard Cite

Hardware Trojans can take various forms to manifest an integrated circuit (IC), causing altered functional behavior, and potential critical consequences, e.g., leaking secret information in encryption applications. This paper presents an approach that uses over-clocking to produce different bit flip patterns between clean design and Trojan-inserted design. Consequently, we apply machine learning algorithms to learn the bit flips distribution at the output of an IC, and therefore differentiate the divergence in the pattern of bit flips caused by the Trojan in IC from its baseline distribution. This approach is effective in detecting Trojan placed off the critical path. The proposed technique is evaluated on benchmarks from Trust-hub and show a detection accuracy of 87%.

show abstract

“…Pre‐silicon and post‐silicon Trojan detection techniques are also needed to be applied. Overhead : The cost of developing CAD tools independently is high. However, there will be security threats when using third‐party CAD tools. Case studies : Pilato et al [86] demonstrated the CAD threats by compromising a high‐level synthesis tool to insert three HTs. The payloads of these Trojans are adding latency, compromising the security of crypto‐cores, and draining energy, respectively.…”

Section: Cad Tools Attacksmentioning

confidence: 99%

“…Case studies : Pilato et al [86] demonstrated the CAD threats by compromising a high‐level synthesis tool to insert three HTs. The payloads of these Trojans are adding latency, compromising the security of crypto‐cores, and draining energy, respectively.…”

Section: Cad Tools Attacksmentioning

confidence: 99%

Ten years of hardware Trojans: a survey from the attacker's perspective

Xue

Liu

et al. 2020

IET Computers & Digital Techniques

View full text Add to dashboard Cite

In the last decade, hardware Trojan has emerged as a serious concern in integrated circuit (IC) industry. As such, hardware Trojan detection techniques have been studied extensively. However, in order to develop reliable and effective defenses, it is important to figure out how hardware Trojans are implemented in practical scenarios. In this paper, we attempt to make a review of the hardware Trojan design and implementations in the last decade and also provide an outlook. Unlike all previous surveys that discuss Trojans from the defender's perspective, for the first time, we study the Trojans from the attacker's perspective, focusing on the attacker's methods, capabilities and challenges when he designs and implements a hardware Trojan. Particularly, the following questions are explored. What are the current methods and capabilities of attackers after ten years of research and development? By considering more and more sophisticated hardware Trojan detection techniques, what challenges do the attackers face, and vice versa? First, we present adversarial models in terms of the adversary's methods, adversary's capabilities and adversary's challenges in seven practical hardware Trojan implementation scenarios: in-house design team attacks, third-party intellectual property (3PIP) vendor attacks, computer-aided design (CAD) tools attacks, fabrication stage attacks, testing stage attacks, distribution stage attacks, and field programmable gate array (FPGA) Trojan attacks. Second, we analyze the hardware Trojan implementation methods under each adversarial model in terms of seven aspects/metrics: hardware Trojan attack scenarios, the attacker's motivation, feasibility (the practicality of the attacks), detectability (anti-detection capability of that kind of Trojan), protection and prevention suggestions for the designer, overhead analysis, and case studies of Trojan implementations. Finally, future directions on hardware Trojan attacks and defenses are discussed. This paper also presents several new insights and assumptions for the first time, including considering the Trojans not only from the copyright owner's perspective, but also from the users' perspective, and discussing the hardware Trojan attacks in the testing phase and in the distribution phase. This paper can hopefully provide a reference for future works on building effective hardware Trojan defenses.

show abstract

Black-Hat High-Level Synthesis: Myth or Reality?

Cited by 19 publications

References 31 publications

Two Sides of the Same Coin: Boons and Banes of Machine Learning in Hardware Security

Two Sides of the Same Coin: Boons and Banes of Machine Learning in Hardware Security

Can Overclocking Detect Hardware Trojans?

Ten years of hardware Trojans: a survey from the attacker's perspective

Contact Info

Product

Resources

About