Defending Against Unforeseen Failure Modes with Latent Adversarial
Training

Defending Against Unforeseen Failure Modes with Latent Adversarial Training

8 March 2024

Lennart Schulze

Dylan Hadfield-Menell

Papers citing "Defending Against Unforeseen Failure Modes with Latent Adversarial Training"

18 / 18 papers shown

Title
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities Zora Che Stephen Casper Robert Kirk Anirudh Satheesh Stewart Slocum ... Zikui Cai Bilal Chughtai Y. Gal Furong Huang Dylan Hadfield-Menell MU AAML ELM 85 3 0 03 Feb 2025
Estimating the Probabilities of Rare Outputs in Language Models Gabriel Wu Jacob Hilton AAML UQCV 48 2 0 17 Oct 2024
Erasing Conceptual Knowledge from Language Models Rohit Gandikota Sheridan Feucht Samuel Marks David Bau KELM ELM MU 44 6 0 03 Oct 2024
Robust LLM safeguarding via refusal feature adversarial training L. Yu Virginie Do Karen Hambardzumyan Nicola Cancedda AAML 62 10 0 30 Sep 2024
Recent Advances in Attack and Defense Approaches of Large Language Models Jing Cui Yishi Xu Zhewei Huang Shuchang Zhou Jianbin Jiao Junge Zhang PILM AAML 57 1 0 05 Sep 2024
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits Andis Draguns Andrew Gritsevskiy S. Motwani Charlie Rogers-Smith Jeffrey Ladish Christian Schroeder de Witt 40 2 0 03 Jun 2024
Attacking Large Language Models with Projected Gradient Descent Simon Geisler Tom Wollschlager M. H. I. Abdalla Johannes Gasteiger Stephan Günnemann AAML SILM 49 50 0 14 Feb 2024
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space Leo Schwinn David Dobre Sophie Xhonneux Gauthier Gidel Stephan Gunnemann AAML 51 38 0 14 Feb 2024
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications Boyi Wei Kaixuan Huang Yangsibo Huang Tinghao Xie Xiangyu Qi Mengzhou Xia Prateek Mittal Mengdi Wang Peter Henderson AAML 60 79 0 07 Feb 2024
Black-Box Access is Insufficient for Rigorous AI Audits Stephen Casper Carson Ezell Charlotte Siegmann Noam Kolt Taylor Lynn Curtis ... Michael Gerovitch David Bau Max Tegmark David M. Krueger Dylan Hadfield-Menell AAML 34 78 0 25 Jan 2024
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity Andrew Lee Xiaoyan Bai Itamar Pres Martin Wattenberg Jonathan K. Kummerfeld Rada Mihalcea 77 96 0 03 Jan 2024
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks Erfan Shayegani Md Abdullah Al Mamun Yu Fu Pedram Zaree Yue Dong Nael B. Abu-Ghazaleh AAML 147 146 0 16 Oct 2023
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned Deep Ganguli Liane Lovitt John Kernion Amanda Askell Yuntao Bai ... Nicholas Joseph Sam McCandlish C. Olah Jared Kaplan Jack Clark 225 446 0 23 Aug 2022
Linear Connectivity Reveals Generalization Strategies Jeevesh Juneja Rachit Bansal Kyunghyun Cho João Sedoc Naomi Saphra 242 45 0 24 May 2022
Fine-tuned Language Models are Continual Learners Thomas Scialom Tuhin Chakrabarty Smaranda Muresan CLL LRM 145 117 0 24 May 2022
Unsolved Problems in ML Safety Dan Hendrycks Nicholas Carlini John Schulman Jacob Steinhardt 186 273 0 28 Sep 2021
FreeLB: Enhanced Adversarial Training for Natural Language Understanding Chen Zhu Yu Cheng Zhe Gan S. Sun Tom Goldstein Jingjing Liu AAML 229 438 0 25 Sep 2019
ImageNet Large Scale Visual Recognition Challenge Olga Russakovsky Jia Deng Hao Su J. Krause S. Satheesh ... A. Karpathy A. Khosla Michael S. Bernstein Alexander C. Berg Li Fei-Fei VLM ObjD 296 39,198 0 01 Sep 2014