Circumventing interpretability: How to defeat mind-readers

21 December 2022

Papers citing "Circumventing interpretability: How to defeat mind-readers"

12 / 12 papers shown

Title
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 181 366 0 21 Sep 2022
Adversarially trained neural representations may already be as robust as corresponding biological neural representations Chong Guo Michael J. Lee Guillaume Leclerc Joel Dapello Yug Rao Aleksander Madry J. DiCarlo GAN AAML 32 13 0 19 Jun 2022
Planting Undetectable Backdoors in Machine Learning Models S. Goldwasser Michael P. Kim Vinod Vaikuntanathan Or Zamir AAML 45 71 0 14 Apr 2022
Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning Arezoo Rajabi Bhaskar Ramasubramanian Radha Poovendran AAML 102 5 0 25 Mar 2022
An Interpretability Illusion for BERT Tolga Bolukbasi Adam Pearce Ann Yuan Andy Coenen Emily Reif Fernanda Viégas Martin Wattenberg MILM FAtt 67 79 0 14 Apr 2021
An overview of 11 proposals for building safe advanced AI Evan Hubinger AAML 51 23 0 04 Dec 2020
Shortcut Learning in Deep Neural Networks Robert Geirhos J. Jacobsen Claudio Michaelis R. Zemel Wieland Brendel Matthias Bethge Felix Wichmann 201 2,048 0 16 Apr 2020
Weight Poisoning Attacks on Pre-trained Models Keita Kurita Paul Michel Graham Neubig AAML SILM 134 451 0 14 Apr 2020
Interval timing in deep reinforcement learning agents B. Deverett Ryan Faulkner Meire Fortunato Greg Wayne Joel Z Leibo 39 14 0 31 May 2019
Universal Transformers Mostafa Dehghani Stephan Gouws Oriol Vinyals Jakob Uszkoreit Lukasz Kaiser 83 752 0 10 Jul 2018
Building machines that adapt and compute like brains Brenden M. Lake J. Tenenbaum AI4CE FedML NAI AILaw 320 887 0 11 Nov 2017
Concrete Problems in AI Safety Dario Amodei C. Olah Jacob Steinhardt Paul Christiano John Schulman Dandelion Mané 220 2,384 0 21 Jun 2016