• Publications
  • Influence
STRIP: a defence against trojan attacks on deep neural networks
TLDR
A recent trojan attack on deep neural network (DNN) models is one insidious variant of data poisoning attacks. Expand
  • 105
  • 17
  • PDF
Obfuscated challenge-response: A secure lightweight authentication mechanism for PUF-based pervasive devices
TLDR
We propose a secure and lightweight authentication protocol for resource scarce pervasive devices built upon a physical unclonable function (PUF) primitive and a variant of a parameter-based authentication protocol. Expand
  • 41
  • 6
  • PDF
PUF-FSM: A Controlled Strong PUF
TLDR
We present a hybrid PUF–finite state machine (PUF-FSM) construction to realize a controlled strong PUF and demonstrate improved security, especially to reliability-based attacks. Expand
  • 25
  • 6
  • PDF
Emerging Physical Unclonable Functions With Nanotechnology
Physical unclonable functions (PUFs) are increasingly used for authentication and identification applications as well as the cryptographic key generation. An important feature of a PUF is theExpand
  • 87
  • 4
  • PDF
Memristive crypto primitive for building highly secure physical unclonable functions
TLDR
We exploit the extremely large information density available in nanocrossbar architectures and the significant resistance variations of memristors to develop an on-chip memristive device based strong PUF (mrSPUF). Expand
  • 63
  • 2
  • PDF
mrPUF: A Novel Memristive Device Based Physical Unclonable Function
TLDR
In this paper we exploit the extremely large information density available in the nanocrossbar architecture and the large resistance variations of memristors to develop on-chip memristive device based PUF (mrPUF). Expand
  • 22
  • 1
  • PDF
PUF Sensor: Exploiting PUF Unreliability for Secure Wireless Sensing
TLDR
We develop an authenticated sensing protocol that is robust against eavesdropping, also capable of detecting man-in-the-middle manipulation of the sensed value. Expand
  • 19
  • 1
Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?
TLDR
A new collaborative learning, called split learning, was recently introduced. Expand
  • 12
  • 1
  • PDF
Lightweight (Reverse) Fuzzy Extractor With Multiple Reference PUF Responses
TLDR
A physical unclonable function (PUF), like a fingerprint, exploits manufacturing randomness to endow each physical item with a unique identifier. Expand
  • 11
  • 1
  • PDF
Building Secure SRAM PUF Key Generators on Resource Constrained Devices
TLDR
A securely maintained key is the premise upon which data stored and transmitted by ubiquitously deployed resource limited devices, such as those in the Internet of Things, are protected. Expand
  • 4
  • 1
  • PDF
...
1
2
3
4
5
...