Machine learning resistant strong PUF: Possible or a pipe dream?

Vijayakumar, Arunkumar; Patil, Vinay C.; Prado, Charles B.; Kundu, Sandip

doi:10.1109/hst.2016.7495550

Cited by 77 publications

(48 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first category is designbased where the defense mechanism is added in the architectural design of the PUFs such as adding non-linearity using XOR logics [6], [7], modifying transistor-level design [8], exploiting FPGA blocks [9], [10] and analogizing the digital components [11]. The second category is the obfuscation-based where the defense mechanism is performed masking of either challenges [12] or responses [2], [13].…”

Section: Background Of the Problemmentioning

confidence: 99%

“…All the defense mechanisms resist or at least improve the resiliency of the PUFs against the ML-MA however they come with some shortcomings. In the case of design-based defense mechanisms, adding non-linearity using XOR [6], [7], analogizing the digital components [11] and exploiting the FPGA blocks [4], [10] increase the hardware overhead.…”

Section: Background Of the Problemmentioning

confidence: 99%

“…As for other machine learning algorithm such as Bagging and Boosting (B & B), it was first used by Vijayakumar et al [7] to perform modeling attacks on strong PUFs. B & B are considered as ensemble meta-algorithm approaches as described by Schapire [58].…”

Section: ) Attacks On Strong Pufsmentioning

confidence: 99%

“…www.ijacsa.thesai.org Table 1, the defense mechanisms that were proposed can be divided into three categories namely design, obfuscation and access control. The design category consists of adding non-linearity using XOR logics [6], [7], configuring transistor's gate sizes [62], augmenting interconnects [63], tightening the layout condition [8], exploiting FPGA resources and reconfigurability [9], [10] and modify current PUF design blocks by using analog blocks [11] and reducing feed-forward stages [64]. These defense mechanisms provide resistance to machine learning modeling attacks however they come with certain shortcomings.…”

Section: Comparison Analysis Of Defense Mechanisms Against Attacksmentioning

confidence: 99%

See 3 more Smart Citations

Defense Mechanisms against Machine Learning Modeling Attacks on Strong Physical Unclonable Functions for IOT Authentication: A Review

Noor¹,

Daud²,

Ahmad³

et al. 2017

ijacsa

View full text Add to dashboard Cite

Abstract-Security component in IoT system are very crucial because the devices within the IoT system are exposed to numerous malicious attacks. Typical security components in IoT system performs authentication, authorization, message and content integrity check. Regarding authentication, it is normally performed using classical authentication scheme using crypto module. However, the utilization of the crypto module in IoT authentication is not feasible because of the distributed nature of the IoT system which complicates the message cipher and decipher process. Thus, the Physical Unclonable Function (PUF) is suggested to replace crypto module for IoT authentication because it only utilizes responses from set of challenges instead of cryptographic keys to authenticate devices. PUF can generate large number of challenge-response pairs (CRPs) which is good for authentication because the unpredictability is high. However, with the emergence of machine learning modeling, the CRPs now can be predicted through machine learning algorithms. Various defense mechanisms were proposed to counter machine learning modeling attacks (ML-MA). Although they were experimentally proven to be able to increase resiliency against ML-MA, they caused the generated responses to be instable and incurred high area overhead. Thus, there is a need to design the best defense mechanism which is not only resistant to ML-MA but also produces reliable responses and reduces area overhead. This paper presents an analysis on defense mechanisms against ML-MA on strong PUFs for IoT authentication.

show abstract

Section: Background Of the Problemmentioning

confidence: 99%

Section: Background Of the Problemmentioning

confidence: 99%

Section: ) Attacks On Strong Pufsmentioning

confidence: 99%

Section: Comparison Analysis Of Defense Mechanisms Against Attacksmentioning

confidence: 99%

See 2 more Smart Citations

Defense Mechanisms against Machine Learning Modeling Attacks on Strong Physical Unclonable Functions for IOT Authentication: A Review

Noor¹,

Daud²,

Ahmad³

et al. 2017

ijacsa

View full text Add to dashboard Cite

show abstract

“…Logistic regression (LR) and evolution strategies (ES) are two ML techniques used in ML‐based modeling attacks. In a previous study , these methods were utilized to evaluate the resistances of APUF, ROPUF, XOR‐PUF, FF‐APUF, and LSPUF in operating modeling attacks. Nevertheless, ML‐based attacks perform poorly with increasing number of XORs and bit‐length of PUFs.…”

Section: Introductionmentioning

confidence: 99%

Design and implementation of an improved MA‐APUF with higher uniqueness and security

Chen

Dan

2020

ETRI Journal

View full text Add to dashboard Cite

An arbiter physical unclonable function (APUF) has exponential challenge‐response pairs and is easy to implement on field‐programmable gate arrays (FPGAs). However, modeling attacks based on machine learning have become a serious threat to APUFs. Although the modeling‐attack resistance of an MA‐APUF has been improved considerably by architecture modifications, the response generation method of an MA‐APUF results in low uniqueness. In this study, we demonstrate three design problems regarding the low uniqueness that APUF‐based strong PUFs may exhibit, and we present several foundational principles to improve the uniqueness of APUF‐based strong PUFs. In particular, an improved MA‐APUF design is implemented in an FPGA and evaluated using a well‐established experimental setup. Two types of evaluation metrics are used for evaluation and comparison. Furthermore, evolution strategies, logistic regression, and K‐junta functions are used to evaluate the security of our design. The experiment results reveal that the uniqueness of our improved MA‐APUF is 81.29% (compared with that of the MA‐APUF, 13.12%), and the prediction rate is approximately 56% (compared with that of the MA‐APUF (60%‐80%).

show abstract

Printable Epsilon‐Type Structure Transistor Arrays with Highly Reliable Physical Unclonable Functions

et al. 2023

View full text Add to dashboard Cite

With rapid development of emerging applications, especially the artificial intelligence and Internet of Things (IoT), a large amount of digital information needs to be replicated, stored, processed, and communicated. This in turn requires secure communication and/or authentication; for this, cryptographic keys are required. [1,2] Software-based data encryption methods based on pseudorandom number generators are no longer sufficient due to their vulnerability; encryption effectiveness is also affected by the key quality. [3] These concerns essentially force the future data-intensive applications to have builtin-hardware-based information security systems, rather than relying solely on the software for battling security attacks. However, traditional hardware encryption solutions often work by storing the keys used by different encryption algorithms in a nonvolatile memory array; the stored cryptographic keys are vulnerable to physical and side-channel attacks, such as by observing the power consumed or radiation emitted. [4] Therefore, an epochmaking hardware-security technology is urgently needed for the future technologies.Physical unclonable functions (PUFs), also known as the physical one-way functions, [5] are promising hardware security primitives that allow random, unique cryptographic keys to be extracted for different application scenarios, rather than being stored in nonvolatile memory arrays. PUFs utilize intrinsic manufacturing defects in the physical microstructure of hardware components to interact with different external stimuli (light, voltage, and magnetic field), to produce unclonable cryptographic primitives comparable to biometrics for hardware security authorization. [6] The first reported PUFs exploited specific 2D patterns generated by a nonuniform 3D structure being optically hashed. [5] In general, optical PUF requires bulky external equipment and is incompatible with the existing silicon fabrication processes, which hinders its further application. [7] Additionally, conventional silicon PUFs suffer from issues such as low entropy, susceptibility to noise interference, and inability to resist machine-learning (ML) attacks. [8,9] In recent years, several PUFs constructed using novel materials, such Printed electronics promises to drive the future data-intensive technologies, with its potential to fabricate novel devices over a large area with low cost on nontraditional substrates. In these emerging technologies, there exists a large digital information flow, which requires secure communication and authentication. Physical unclonable functions (PUFs) offer a promising builtin hardware-security system comparable to biometrical data, which can be constructed by device-specific intrinsic variations in the additive manufacturing process of active devices. However, printed PUFs typically exploit the inherent variation in layer thickness and roughness of active devices. The current in devices with enough significant changes to increase the robustness to external environment noise is still a challen...

show abstract

Machine learning resistant strong PUF: Possible or a pipe dream?

Cited by 77 publications

References 14 publications

Defense Mechanisms against Machine Learning Modeling Attacks on Strong Physical Unclonable Functions for IOT Authentication: A Review

Defense Mechanisms against Machine Learning Modeling Attacks on Strong Physical Unclonable Functions for IOT Authentication: A Review

Design and implementation of an improved MA‐APUF with higher uniqueness and security

Printable Epsilon‐Type Structure Transistor Arrays with Highly Reliable Physical Unclonable Functions

Contact Info

Product

Resources

About