65 citations · 162 across the 30 of their papers we have counts for
6 papers · 1 filter
On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
Md Imran Hossen, Xiali Hei
The advent of instruction-tuned Large Language Models designed for coding tasks (Code LLMs) has transformed software engineering practices. However, their robustness against variou…
Practitioner Paper: Decoding Intellectual Property: Acoustic and Magnetic Side-channel Attack on a 3D Printer
Amirhossein Jamarani, Yazhou Tu, Xiali Hei
The widespread accessibility and ease of use of additive manufacturing (AM), widely recognized as 3D printing, has put Intellectual Property (IP) at great risk of theft. As 3D prin…
Securing the Future: Exploring Privacy Risks and Security Questions in Robotic Systems
Diba Afroze, Yazhou Tu, Xiali Hei
The integration of artificial intelligence, especially large language models in robotics, has led to rapid advancements in the field. We are now observing an unprecedented surge in…
Can't say cant? Measuring and Reasoning of Dark Jargons in Large Language Models
Xu Ji, Jianyi Zhang, Ziyin Zhou +5
Ensuring the resilience of Large Language Models (LLMs) against malicious exploitation is paramount, with recent focus on mitigating offensive responses. Yet, the understanding of…
Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
Md Imran Hossen, Sai Venkatesh Chilukoti, Liqun Shan +3
Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications ari…
Facebook Report on Privacy of fNIRS data
Md Imran Hossen, Sai Venkatesh Chilukoti, Liqun Shan +2
The primary goal of this project is to develop privacy-preserving machine learning model training techniques for fNIRS data. This project will build a local model in a centralized…