PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips

v1v2 (latest)

PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips

10 December 2024

Zachary Coalson

Prashant J. Nair

ArXiv (abs)PDF HTML

Papers citing "PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips"

6 / 56 papers shown

Title
Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search Adnan Siraj Rakin Zhezhi He Deliang Fan AAML 84 224 0 28 Mar 2019
How Important Is a Neuron? Kedar Dhamdhere Mukund Sundararajan Qiqi Yan FAtt GNN 68 131 0 30 May 2018
Another Flip in the Wall of Rowhammer Defenses Daniel Gruss Moritz Lipp Michael Schwarz Daniel Genkin Jonas Juffinger Sioli O'Connell Wolfgang Schoechl Y. Yarom 78 256 0 02 Oct 2017
Attention Is All You Need Ashish Vaswani Noam M. Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan Gomez Lukasz Kaiser Illia Polosukhin 3DV 808 132,725 0 12 Jun 2017
DRAMA: Exploiting DRAM Addressing for Cross-CPU Attacks P. Pessl Daniel Gruss Clémentine Maurice Michael Schwarz Stefan Mangard 84 456 0 27 Nov 2015
Rowhammer.js: A Remote Software-Induced Fault Attack in JavaScript Daniel Gruss Clémentine Maurice Stefan Mangard 99 423 0 24 Jul 2015