Can Go AIs be adversarially robust?

Kotlopou1 pts0 comments

[2406.12843] Can Go AIs be adversarially robust?

-->

Computer Science > Machine Learning

arXiv:2406.12843 (cs)

[Submitted on 18 Jun 2024 (v1), last revised 14 Jan 2025 (this version, v3)]

Title:Can Go AIs be adversarially robust?

Authors:Tom Tseng, Euan McLean, Kellin Pelrine, Tony T. Wang, Adam Gleave<br>View a PDF of the paper titled Can Go AIs be adversarially robust?, by Tom Tseng and 4 other authors

View PDF

Abstract:Prior work found that superhuman Go AIs can be defeated by simple adversarial strategies, especially "cyclic" attacks. In this paper, we study whether adding natural countermeasures can achieve robustness in Go, a favorable domain for robustness since it benefits from incredible average-case capability and a narrow, innately adversarial setting. We test three defenses: adversarial training on hand-constructed positions, iterated adversarial training, and changing the network architecture. We find that though some of these defenses protect against previously discovered attacks, none withstand freshly trained adversaries. Furthermore, most of the reliably effective attacks these adversaries discover are different realizations of the same overall class of cyclic attacks. Our results suggest that building robust AI systems is challenging even with extremely superhuman systems in some of the most tractable settings, and highlight two key gaps: efficient generalization of defenses, and diversity in training. For interactive examples of attacks and a link to our codebase, see this https URL.

Comments:<br>63 pages, AAAI 2025

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)

Cite as:<br>arXiv:2406.12843 [cs.LG]

(or<br>arXiv:2406.12843v3 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2406.12843

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Tom Tseng [view email]<br>[v1]<br>Tue, 18 Jun 2024 17:57:49 UTC (3,528 KB)

[v2]<br>Tue, 24 Sep 2024 08:38:38 UTC (3,596 KB)

[v3]<br>Tue, 14 Jan 2025 03:08:02 UTC (2,089 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Can Go AIs be adversarially robust?, by Tom Tseng and 4 other authors<br>View PDF<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2024-06

Change to browse by:

cs<br>cs.AI<br>stat<br>stat.ML

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

toggle arxiv robust view adversarially paper

Related Articles