# Log-normal Mutations and their Use in Detecting Surreptitious Fake Images

arXiv: https://arxiv.org/abs/2409.15119 · HTML: https://mlsanity.com/paper/2409.15119/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022)
- [Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks](https://mlsanity.com/paper/2310.00076/) (2023)
- [Evading Watermark based Detection of AI-Generated Content](https://mlsanity.com/paper/2305.03807/) (2023)
- [Online Detection of AI-Generated Images](https://mlsanity.com/paper/2310.15150/) (2023)
- [Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality](https://mlsanity.com/paper/2307.02347/) (2023)
- [IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristics](https://mlsanity.com/paper/1810.05281/) (2018)
- [Versatile Black-Box Optimization](https://mlsanity.com/paper/2004.14014/) (2020)
- [Benchmarking Discrete Optimization Heuristics with IOHprofiler](https://mlsanity.com/paper/1912.09237/) (2019)
- [Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking](https://mlsanity.com/paper/2010.04542/) (2020)
- [Self-Adjusting Mutation Rates with Provably Optimal Success Rules](https://mlsanity.com/paper/1902.02588/) (2019)
- [Detecting Images Generated by Diffusers](https://mlsanity.com/paper/2303.05275/) (2023)
- [CMA-ES with Margin: Lower-Bounding Marginal Probability for Mixed-Integer Black-Box Optimization](https://mlsanity.com/paper/2205.13482/) (2022)
- [Detecting AI-Generated Images via CLIP](https://mlsanity.com/paper/2404.08788/) (2024)
- [The (1+λ) Evolutionary Algorithm with Self-Adjusting Mutation Rate](https://mlsanity.com/paper/1704.02191/) (2017)
- [The linear hidden subset problem for the (1+1) EA with scheduled and adaptive mutation rates](https://mlsanity.com/paper/1808.05566/) (2018)
- [An Improved Generic Bet-and-Run Strategy for Speeding Up Stochastic Local Search](https://mlsanity.com/paper/1806.08984/) (2018)
- [Interpolating Local and Global Search by Controlling the Variance of Standard Bit Mutation](https://mlsanity.com/paper/1901.05573/) (2019)
- [When to be Discrete: Analyzing Algorithm Performance on Discretized Continuous Problems](https://mlsanity.com/paper/2304.13117/) (2023)

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

- [Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models](https://mlsanity.com/paper/2510.20468/) (2025)

## Abstract (arXiv)

In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial attacks. However, these attacks are easily detected due to their specific initial distribution. We therefore consider other black-box attacks, inspired from generic black-box optimization tools, and in particular the log-normal algorithm. We apply the log-normal method to the attack of fake detectors, and get successful attacks: importantly, these attacks are not detected by detectors specialized on classical adversarial attacks. Then, combining these attacks and deep detection, we create improved fake detectors.