# Dynamic Probabilistic Noise Injection for Membership Inference Defense

arXiv: https://arxiv.org/abs/2505.13362 · HTML: https://mlsanity.com/paper/2505.13362/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 18 of 18)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Parseval Networks: Improving Robustness to Adversarial Examples](https://mlsanity.com/paper/1704.08847/) (2017)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [Sensitivity and Generalization in Neural Networks: an Empirical Study](https://mlsanity.com/paper/1802.08760/) (2018)
- [Machine Learning with Membership Privacy using Adversarial Regularization](https://mlsanity.com/paper/1807.05852/) (2018)
- [Deep Learning in Mobile and Wireless Networking: A Survey](https://mlsanity.com/paper/1803.04311/) (2018)
- [Rethinking LLM Memorization through the Lens of Adversarial Compression](https://mlsanity.com/paper/2404.15146/) (2024)
- [A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks](https://mlsanity.com/paper/2306.07303/) (2023)
- [Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture](https://mlsanity.com/paper/2110.08324/) (2021)
- [Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks](https://mlsanity.com/paper/2006.14042/) (2020)
- [RelaxLoss: Defending Membership Inference Attacks without Losing Utility](https://mlsanity.com/paper/2207.05801/) (2022)
- [Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction](https://mlsanity.com/paper/2307.01610/) (2023)
- [Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks](https://mlsanity.com/paper/2405.20641/) (2024)

## Built on by (most cited first, 1 of 1)

- [When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI](https://mlsanity.com/paper/2605.03213/) (2026)

## Abstract (arXiv)

Membership Inference Attacks (MIAs) expose privacy risks by determining whether a specific sample was part of a model's training set. These threats are especially serious in sensitive domains such as healthcare and finance. Traditional mitigation techniques, such as static differential privacy, rely on injecting a fixed amount of noise during training or inference. However, this often leads to a detrimental trade-off: the noise may be insufficient to counter sophisticated attacks or, when increased, can substantially degrade model accuracy. To address this limitation, we propose DynaNoise, an adaptive inference-time defense that modulates injected noise based on per-query sensitivity. DynaNoise estimates risk using measures such as Shannon entropy and scales the noise variance accordingly, followed by a smoothing step that re-normalizes the perturbed outputs to preserve predictive utility. We further introduce MIDPUT (Membership Inference Defense Privacy-Utility Trade-off), a scalar metric that captures both privacy gains and accuracy retention. Our evaluation on several benchmark datasets demonstrates that DynaNoise substantially lowers attack success rates while maintaining competitive accuracy, achieving strong overall MIDPUT scores compared to state-of-the-art defenses.