Symmetry Defeats Auditing
Cryptography and Security
2026-05-28 v1 Artificial Intelligence
Abstract
We demonstrate an attack on Introspection Adapters (Shenoy et al., 2026).
Cite
@article{arxiv.2605.27836,
title = {Symmetry Defeats Auditing},
author = {Nick Merrill and Zeke Medley},
journal= {arXiv preprint arXiv:2605.27836},
year = {2026}
}
Related papers
View all related →
Cryptography and Security · Computer Science
A Note on Implementation Errors in Recent Adaptive Attacks Against Multi-Resolution Self-Ensembles
Stanislav Fort
2025-01-27
Cryptography and Security · Computer Science
Revisiting the Robust Alignment of Circuit Breakers
Leo Schwinn, Simon Geisler
2024-08-05
Machine Learning · Computer Science
Symmetry Defense Against CNN Adversarial Perturbation Attacks
Blerta Lindqvist
2023-08-11
Neural and Evolutionary Computing · Computer Science
Adversarial Images for Variational Autoencoders
Pedro Tabacof, Julia Tavares, Eduardo Valle
2016-12-02
Cryptography and Security · Computer Science
One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries
Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky
2026-05-26
Machine Learning · Computer Science
Encoding Involutory Invariances in Neural Networks
Anwesh Bhattacharya, Marios Mattheakis, Pavlos Protopapas
2022-04-28
chao-dyn · Physics
Identification and Control of Symmetric Systems
R. O. Grigoriev
2007-05-23
Computer Vision and Pattern Recognition · Computer Science
Attacking Perceptual Similarity Metrics
Abhijay Ghildyal, Feng Liu
2023-05-16
Cosmology and Nongalactic Astrophysics · Physics
Lost in the Log-Polynomial Expansion: Comment on arXiv:2101.08278
Aritra Banerjee, Eoin Ó Colgáin, Misao Sasaki, M. M. Sheikh-Jabbari
2021-06-01
Neural and Evolutionary Computing · Computer Science
Symmetry Breaking in Neuroevolution: A Technical Report
Onay Urfalioglu, Orhan Arikan
2011-07-25
Combinatorics · Mathematics
Projections, Entropy and Sumsets
Paul Balister, Béla Bollobás
2017-01-10
Optimization and Control · Mathematics
Symmetry reduction in AM/GM-based optimization
Philippe Moustrou, Helen Naumann, Cordian Riener, Thorsten Theobald +1
2021-12-09
Machine Learning · Computer Science
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It
Marvin F. da Silva, Felix Dangel, Sageev Oore
2025-05-09
Mathematical Physics · Physics
Symmetry problem
Alexander G. Ramm
2014-02-14
Artificial Intelligence · Computer Science
Adaptive auditing of AI systems with anytime-valid guarantees
Siyu Zhou, Patrick Vossler, Venkatesh Sivaraman, Yifan Mai +1
2026-05-11
Computer Vision and Pattern Recognition · Computer Science
Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving
Kangqiao Zhao, Shuo Huai, Xurui Song, Jun Luo
2026-03-17
Classical Analysis and ODEs · Mathematics
On self-similar sets with overlaps and inverse theorems for entropy in $\mathbb{R}^d$
Michael Hochman
2017-06-07
Cryptography and Security · Computer Science
HBEE: Human Behavioral Entropy Engine -- Pre-Registered Multi-Agent LLM Simulation of Peer-Suspicion-Based Detection Inversion
Vickson Ferrel
2026-05-11
Machine Learning · Computer Science
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
Florian Tramèr
2022-06-17
Artificial Intelligence · Computer Science
Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning
Nathan Gavenski, Felipe Meneguzzi, Odinaldo Rodrigues
2026-02-24
Machine Learning · Computer Science
On Adaptive Attacks to Adversarial Example Defenses
Florian Tramer, Nicholas Carlini, Wieland Brendel, Aleksander Madry
2020-10-26
Computational Complexity · Computer Science
From expanders to hitting distributions and simulation theorems
Alexander Kozachinskiy
2018-07-09
Information Theory · Computer Science
Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation
Weihao Gao, Sewoong Oh, Pramod Viswanath
2016-09-09
Computer Science and Game Theory · Computer Science
Geometrical Regret Matching
Sizhong Lan
2020-01-24
Computer Vision and Pattern Recognition · Computer Science
See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation
Darren Tsai, Julie Stephany Berrio, Mao Shan, Stewart Worrall +1
2023-04-12