Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
31 of 57 references.
References · 31
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
- 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
- 2022Diffusion Models for Adversarial Purificationcited by 476
- 2023DIRE for Diffusion-Generated Image Detectioncited by 390
- 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
- 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
- 2019Simple Black-box Adversarial Attackscited by 251
19 more
- 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Modelscited by 168
- 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attackscited by 81
- 2023Evading Watermark based Detection of AI-Generated Contentcited by 78
- 2023Online Detection of AI-Generated Imagescited by 55
- 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
- 2018IOHprofiler: A Benchmarking and Profiling Tool for Iterative Optimization Heuristicscited by 28
- 2020Versatile Black-Box Optimizationcited by 22
- 2019Benchmarking Discrete Optimization Heuristics with IOHprofilercited by 14
- 2020Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarkingcited by 14
- 2019Self-Adjusting Mutation Rates with Provably Optimal Success Rulescited by 13
- 2023Detecting Images Generated by Diffuserscited by 12
- 2022CMA-ES with Margin: Lower-Bounding Marginal Probability for Mixed-Integer Black-Box Optimizationcited by 6
- 2024Detecting AI-Generated Images via CLIPcited by 5
- 2017The (1+λ) Evolutionary Algorithm with Self-Adjusting Mutation Ratecited by 4
- 2018The linear hidden subset problem for the (1+1) EA with scheduled and adaptive mutation ratescited by 3
- 2018An Improved Generic Bet-and-Run Strategy for Speeding Up Stochastic Local Searchcited by 2
- 2019Interpolating Local and Global Search by Controlling the Variance of Standard Bit Mutationcited by 2
- 2023When to be Discrete: Analyzing Algorithm Performance on Discretized Continuous Problemscited by 2
- 2021A Novel Watermarking Approach for Protecting Image Integrity based on a Hybrid Security Techniquecited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.