ResearchTrend.AI
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
v1v2 (latest)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

Javier Rando
Francesco Croce
Kryvstof Mitka
Stepan Shabalin
Maksym Andriushchenko
Nicolas Flammarion
F. Tramèr
ArXiv (abs)PDFHTML

Papers citing "Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs"

9 / 9 papers shown
Title
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Pankayaraj Pathmanathan
Udari Madhushani Sehwag
Michael-Andrei Panaitescu-Liess
Furong Huang
SILMAAML
82
0
0
15 Oct 2024
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
Andis Draguns
Andrew Gritsevskiy
S. Motwani
Charlie Rogers-Smith
Jeffrey Ladish
Christian Schroeder de Witt
126
2
0
03 Jun 2024
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
Maksym Andriushchenko
Francesco Croce
Nicolas Flammarion
AAML
155
212
0
02 Apr 2024
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Guangyu Shen
Shuyang Cheng
Kai-xian Zhang
Guanhong Tao
Shengwei An
Lu Yan
Zhuo Zhang
Shiqing Ma
Xiangyu Zhang
55
15
0
08 Feb 2024
Universal and Transferable Adversarial Attacks on Aligned Language Models
Universal and Transferable Adversarial Attacks on Aligned Language Models
Andy Zou
Zifan Wang
Nicholas Carlini
Milad Nasr
J. Zico Kolter
Matt Fredrikson
291
1,498
0
27 Jul 2023
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Wenkai Yang
Lei Li
Zhiyuan Zhang
Xuancheng Ren
Xu Sun
Bin He
SILM
89
153
0
29 Mar 2021
Weight Poisoning Attacks on Pre-trained Models
Weight Poisoning Attacks on Pre-trained Models
Keita Kurita
Paul Michel
Graham Neubig
AAMLSILM
134
451
0
14 Apr 2020
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Xinyun Chen
Chang-rui Liu
Yue Liu
Kimberly Lu
Basel Alomair
AAMLSILM
143
1,840
0
15 Dec 2017
Poisoning Attacks against Support Vector Machines
Poisoning Attacks against Support Vector Machines
Battista Biggio
B. Nelson
Pavel Laskov
AAML
115
1,593
0
27 Jun 2012