# Symmetry Defeats Auditing

arXiv: https://arxiv.org/abs/2605.27836 · HTML: https://mlsanity.com/paper/2605.27836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 8 of 8)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models](https://mlsanity.com/paper/2405.16833/) (2024)
- [LoRA vs Full Fine-tuning: An Illusion of Equivalence](https://mlsanity.com/paper/2410.21228/) (2024)
- [Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons](https://mlsanity.com/paper/2406.14144/) (2024)
- [PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models](https://mlsanity.com/paper/2506.20629/) (2025)
- [Introspection Adapters: Training LLMs to Report Their Learned Behaviors](https://mlsanity.com/paper/2604.16812/) (2026)
- [Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs](https://mlsanity.com/paper/2506.18931/) (2025)

## Abstract (arXiv)

We demonstrate an attack on Introspection Adapters (Shenoy et al., 2026).