2 papers
cs.LG2024
LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
Piyush Jha, Arnav Arora, Vijay Ganesh
We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Unlike traditional metho…
cond-mat.mes-hall2023
On the conclusive detection of Majorana zero modes: conductance spectroscopy, disconnected entanglement entropy and the fermion parity noise
Arnav Arora, Abhishek Kejriwal, Bhaskaran Muralidharan
Semiconducting nanowires with strong Rashba spin-orbit coupling in the proximity with a superconductor and under a strong Zeeman field can potentially manifest Majorana zero modes…