8 papers
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Kalyan Nakka, Nitesh Saxena
The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised…
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…
Infrastructure Patterns in Toll Scam Domains: A Comprehensive Analysis of Cybercriminal Registration and Hosting Strategies
Morium Akter Munny, Mahbub Alam, Sonjoy Kumar Paul +3
Toll scams involve criminals registering fake domains that pretend to be legitimate transportation agencies to trick users into making fraudulent payments. Although these scams are…
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…
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…
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…