Yet Another But More Efficient Blackbox Adversarial Attack Tiling And Evolution Strategies
ASecurity**arXiv ID:** 1910.02244 **Authors:** Laurent Meunier, Jamal Atif, Olivier Teytaud **Published:** 2019-10-05T10:36:47Z **Abstract:** We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from $\ell_\infty$-white box attacks, and particularly designed to fit derivative-free optimization requirements. It only requires to have access to the logits of the classifier without any other information which is a m...
- 3 stars
- 0 votes
- 0 copies
- 5 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill yet-another-but-more-efficient-blackbox-adversarial-attack-tiling-and-evolution-strategies --agent claude-codeAre you the author of Yet Another But More Efficient Blackbox Adversarial Attack Tiling And Evolution Strategies?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-yet-another-but-more-efficient-blackbox-adversaria)# Yet another but more efficient black-box adversarial attack: tiling and evolution strategies
**arXiv ID:** 1910.02244
**Authors:** Laurent Meunier, Jamal Atif, Olivier Teytaud
**Published:** 2019-10-05T10:36:47Z
**Abstract:**
We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from $\ell_\infty$-white box attacks, and particularly designed to fit derivative-free optimization requirements. It only requires to have access to the logits of the classifier without any other information which is a more realistic scenario. Not only we introduce a new objective function, we extend previous works on black box adversarial attacks to a larger spectrum of evolution strategies and other derivative-free optimization methods. We also highlight a new intriguing property that deep neural networks are not robust to single shot tiled attacks. Our models achieve, with a budget limited to $10,000$ queries, results up to $99.2\%$ of success rate against InceptionV3 classifier with $630$ queries to the network on average in the untargeted attacks setting, which is an improvement by $90$ queries of the current state of the art. In the targeted setting, we are able to reach, with a limited budget of $100,000$, $100\%$ of success rate with a budget of $6,662$ queries on average, i.e. we need $800$ queries less than the current state of the art.
## Skill Description
This skill is generated from the arXiv paper: Yet another but more efficient black-box adversarial attack: tiling and evolution strategies (1910.02244).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1910.02244](http://arxiv.org/abs/1910.02244v2)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.