Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nakka, Kalyan, Dani, Jimmy, Mondal, Ausmit, Saxena, Nitesh
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models
by: Nakka, Kalyan, et al.
Published: (2024)

A Machine Learning-Based Framework for Assessing Cryptographic Indistinguishability of Lightweight Block Ciphers
by: Dani, Jimmy, et al.
Published: (2024)

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
by: Nakka, Kalyan, et al.
Published: (2025)

When AI Defeats Password Deception! A Deep Learning Framework to Distinguish Passwords and Honeywords
by: Dani, Jimmy, et al.
Published: (2024)

The First Early Evidence of the Use of Browser Fingerprinting for Online Tracking
by: Liu, Zengrui, et al.
Published: (2024)

Robust and Verifiable MPC with Applications to Linear Machine Learning Inference
by: Wang, Tzu-Shen, et al.
Published: (2025)

Opted Out, Yet Tracked: Are Regulations Enough to Protect Your Privacy?
by: Liu, Zengrui, et al.
Published: (2022)

Privacy and Security of Women's Reproductive Health Apps in a Changing Legal Landscape
by: Saini, Shalini, et al.
Published: (2024)

LiteQSign: Lightweight and Quantum-Safe Signatures for Heterogeneous IoT Applications
by: Yavuz, Attila A., et al.
Published: (2023)

PromptKeeper: Safeguarding System Prompts for LLMs
by: Jiang, Zhifeng, et al.
Published: (2024)

LiteRSan: Lightweight Memory Safety Via Rust-specific Program Analysis and Selective Instrumentation
by: Xia, Tianrou, et al.
Published: (2025)

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
by: Lin, Lixing, et al.
Published: (2026)

Safeguarding Smart Inhaler Devices and Patient Privacy in Respiratory Health Monitoring
by: Babajide, Asaju, et al.
Published: (2025)

LiteShield: Hybrid Feature Selection-Driven Lightweight Intrusion Detection for Resource-Constrained IoT Networks
by: Mabulage, Dileepa, et al.
Published: (2026)

Lite-BD: A Lightweight Black-box Backdoor Defense via Reviving Multi-Stage Image Transformations
by: Miah, Abdullah Arafat, et al.
Published: (2026)

TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE
by: Sun, Tong, et al.
Published: (2025)

LiteAtt: A Peer-to-Peer Self-Attestation Framework and Handshake Protocol for Connected IoT Devices
by: Kohli, Varun, et al.
Published: (2026)

The Vulnerability of LLM Rankers to Prompt Injection Attacks
by: Yin, Yu, et al.
Published: (2026)

Safeguarding Graph Neural Networks against Topology Inference Attacks
by: Fu, Jie, et al.
Published: (2025)

ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks
by: Zhuang, Zhixiong, et al.
Published: (2025)

A Quantization-Aware Training Based Lightweight Method for Neural Distinguishers
by: Xiong, Guangwei, et al.
Published: (2026)

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
by: Nakka, Krishna Kanth, et al.
Published: (2025)

VulnScout-C: A Lightweight Transformer for C Code Vulnerability Detection
by: Lassoued, Aymen, et al.
Published: (2026)

Defending Against Prompt Injection with DataFilter
by: Wang, Yizhu, et al.
Published: (2025)

Seamless Website Fingerprinting in Multiple Environments
by: Song, Chuxu, et al.
Published: (2024)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
by: Zhang, Xu, et al.
Published: (2025)

Lite-PoT: Practical Powers-of-Tau Setup Ceremony
by: Ng, Lucien K. L., et al.
Published: (2025)

LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors
by: Lu, Jiajie, et al.
Published: (2025)

The Elephant in the Room: Software and Hardware Security Vulnerabilities of Portable Sequencing Devices
by: Stillman, Carson, et al.
Published: (2024)

Obfuscating Code Vulnerabilities against Static Analysis in JavaScript Code
by: Pagano, Francesco, et al.
Published: (2026)

Infrastructure Patterns in Toll Scam Domains: A Comprehensive Analysis of Cybercriminal Registration and Hosting Strategies
by: Munny, Morium Akter, et al.
Published: (2025)

Distilling Lightweight Language Models for C/C++ Vulnerabilities
by: Wei, Zhiyuan, et al.
Published: (2025)

Developing and Evaluating Lightweight Cryptographic Algorithms for Secure Embedded Systems in IoT Devices
by: Sedraoui, Brahim Khalil, et al.
Published: (2026)

Predicting IoT Device Vulnerability Fix Times with Survival and Failure Time Models
by: A, Carlos A Rivera, et al.
Published: (2025)

A Review on the Security Vulnerabilities of the IoMT against Malware Attacks and DDoS
by: Dzamesi, Lily, et al.
Published: (2025)

PINA: Prompt Injection Attack against Navigation Agents
by: Liu, Jiani, et al.
Published: (2026)

Prompting the Priorities: A First Look at Evaluating LLMs for Vulnerability Triage and Prioritization
by: Haddad, Osama Al, et al.
Published: (2025)

Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities
by: Nong, Yu, et al.
Published: (2024)

Safeguarding Skies: Airport Cybersecurity in the Digital Age
by: Sivakorn, Suphannee, et al.
Published: (2026)

Adaptive Exploit Generation against Security Devices and Security APIs
by: Künnemann, Robert, et al.
Published: (2024)