Ayantika Chatterjee

EHEIR: Efficient Homomorphic Encrypted Inference via Architectural Redesign

Reeshav Chowdhury, Anoop Mishra, Deepak Khazanchi, Ayantika Chatterjee

Encrypted inference under homomorphic encryption (HE) imposes stringent constraints on computation, making the direct deployment of deep neural networks infeasible on resource-constrained edge devices. Existing approaches, such as FHEEDGE and UniHENN, primarily focus on improving the efficiency of encrypted computation through algorithmic …

in, us (code pays fourni par la source)

Transferability of Evasion and Backdoor Attacks in Encrypted Domain

Reeshav Chowdhury, Ayantika Chatterjee

in (code pays fourni par la source)

Related-Key Cryptanalysis of FUTURE

Amit Jana, Smita Das, Ayantika Chatterjee, Debdeep Mukhopadhyay et autres

in, jp (code pays fourni par la source)

SPlatoon: Secure Platoon with Lightweight Authenticated Encryption

Gulabi Mandal, Ipsita Koley, Ayantika Chatterjee, Soumyajit Dey

Vehicle platoons improve road capacity and safety by enabling cooperative driving with small inter-vehicle gaps. Such coordination requires a timely wireless exchange of vehicle state information (speed, position, and acceleration). However, vehicular networks are vulnerable to attacks that can manipulate shared information …

in, se (code pays fourni par la source)

WiperSentinel: HPC Based Wiper Detection with Enhanced AutoEncoder

Shiva Agarwal, Suvadeep Hajra, Ayantika Chatterjee, Debdeep Mukhopadhyay

in (code pays fourni par la source)

An Efficient Circuit Synthesis Framework for TFHE via Convex Sub-graph Optimization

Ayantika Chatterjee, Anupam Chattopadhyay, Debdeep Mukhopadhyay

in, sg (code pays fourni par la source)

SMLaaS: Secure Machine Learning as a Service Ensuring Data and Model Parameter Privacy

B. Rami Reddy, Ayantika Chatterjee

ABSTRACT Attacks against machine learning (ML) models are serious concerns in the case of adapting ML as a Service (MLaaS) for security‐critical applications. Hence, privacy‐preserving ML is an important area of research to protect ML intellectual properties (IPs) like training data, prediction …

in (code pays fourni par la source)

SHELDB: Client Storage Aware Homomorphic Encrypted Database Processing Framework With Low Communication Overhead

Tanusree Parbat, Ayantika Chatterjee

Database as a service (DBaaS) in cloud raises severe concern in terms of data security. Storing data in encrypted form may confirm data confidentiality. But, database processing cannot be supported in this encrypted form. Theoretically, homomorphic encryption is a solution to support …

in (code pays fourni par la source)

ESMDP: Encrypted ML Framework for Secure Medical Data Processing

B. Rami Reddy, Ayantika Chatterjee

in (code pays fourni par la source)

IND-CPA$$^{{\textbf {C}}}$$: A New Security Notion for Conditional Decryption in Fully Homomorphic Encryption

Bhuvnesh Chaturvedi, Anirban Chakraborty, Nimish Mishra, Ayantika Chatterjee et autres

in, de (code pays fourni par la source)

Secure Join and Compute in Encrypted Database

Tanusree Parbat, Ayantika Chatterjee

In public and shared platforms where security is paramount, encrypted database storage and processing have become a key research priority. However, traditionally encrypted databases do not support direct computation of relational queries, and hence, those types of query processing are infeasible without …

in (code pays fourni par la source)

Transferability of Evasion Attacks Against FHE Encrypted Inference

Aman Kumar, Vaibhav Dashrath Mohite, Ayantika Chatterjee

in (code pays fourni par la source)