# Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies

arXiv: https://arxiv.org/abs/2505.22829 · HTML: https://mlsanity.com/paper/2505.22829/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 157 of its 233 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 30 of 157)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)

## Built on by (most cited first, 3 of 3)

- [AI Deception: Risks, Dynamics, and Controls](https://mlsanity.com/paper/2511.22619/) (2025)
- [Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation](https://mlsanity.com/paper/2508.08570/) (2025)
- [Does Weak-to-strong Generalization Happen under Spurious Correlations?](https://mlsanity.com/paper/2509.24005/) (2025)

## Abstract (arXiv)

This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types connections between specific causes of distribution shift and fine-grained AI safety issues: (1) methods addressing a specific shift type can help achieve corresponding safety goals, or (2) certain shifts and safety issues can be formally reduced to each other, enabling mutual adaptation of their methods. Our findings provide a unified perspective that encourages deeper integration between distribution shift and AI safety research.