activity
20242026
collaborators

6 papers

cs.CR2026

LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities

Kalyan Nakka, Jimmy Dani, Ausmit Mondal +1

The growing adoption of Large Language Models (LLMs) has influenced the development of Small Language Models (SLMs) for on-device deployment across smartphones and edge devices, of…

cs.CR2025

Robust and Verifiable MPC with Applications to Linear Machine Learning Inference

Tzu-Shen Wang, Jimmy Dani, Juan Garay +2

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who m…

cs.CR2025

A Machine Learning-Based Framework for Assessing Cryptographic Indistinguishability of Lightweight Block Ciphers

Jimmy Dani, Kalyan Nakka, Nitesh Saxena

Indistinguishability is a fundamental principle of cryptographic security, crucial for securing data transmitted between Internet of Things (IoT) devices. This principle ensures th…

cs.CR2025

Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models

Kalyan Nakka, Jimmy Dani, Nitesh Saxena

In this paper, we present a very first study to investigate trust and ethical implications of on-device artificial intelligence (AI), focusing on small language models (SLMs) amena…

cs.CR2025

The First Early Evidence of the Use of Browser Fingerprinting for Online Tracking

Zengrui Liu, Jimmy Dani, Yinzhi Cao +2

While advertising has become commonplace in today's online interactions, there is a notable dearth of research investigating the extent to which browser fingerprinting is harnessed…

cs.CR2024

When AI Defeats Password Deception! A Deep Learning Framework to Distinguish Passwords and Honeywords

Jimmy Dani, Brandon McCulloh, Nitesh Saxena

"Honeywords" have emerged as a promising defense mechanism for detecting data breaches and foiling offline dictionary attacks (ODA) by deceiving attackers with false passwords. In…