47 citations · 54 across the 8 of their papers we have counts for
8 papers · 1 filter
PAPER: Privacy-Preserving Convolutional Neural Networks using Low-Degree Polynomial Approximations and Structural Optimizations on Leveled FHE
Eduardo Chielle, Manaar Alam, Jinting Liu +2
Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNNs) possible. However, the perfo…
ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
Manaar Alam, Hithem Lamri, Michail Maniatakos
Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences…
RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation
Lakshmi Likhitha Mankali, Jitendra Bhandari, Manaar Alam +4
Large language models (LLMs) have demonstrated remarkable potential with code generation/completion tasks for hardware design. In fact, LLM-based hardware description language (HDL…
LLMPot: Dynamically Configured LLM-based Honeypot for Industrial Protocol and Physical Process Emulation
Christoforos Vasilatos, Dunia J. Mahboobeh, Hithem Lamri +2
Industrial Control Systems (ICS) are extensively used in critical infrastructures ensuring efficient, reliable, and continuous operations. However, their increasing connectivity an…
Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
Shubhi Shukla, Manaar Alam, Pabitra Mitra +1
Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning…
RAPPER: Ransomware Prevention via Performance Counters
Manaar Alam, Sayan Sinha, Sarani Bhattacharya +3
Ransomware can produce direct and controllable economic loss, which makes it one of the most prominent threats in cyber security. As per the latest statistics, more than half of ma…