[2605.22568] Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard

-->

Computer Science > Cryptography and Security

arXiv:2605.22568 (cs)

[Submitted on 21 May 2026]

Title:Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard

Authors:Sahar Abdelnabi, Chris Hicks, Konrad Rieck, Ahmad-Reza Sadeghi<br>View a PDF of the paper titled Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard, by Sahar Abdelnabi and 3 other authors

View PDF<br>HTML (experimental)

Abstract:The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.

Subjects:

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2605.22568 [cs.CR]

(or<br>arXiv:2605.22568v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2605.22568

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Konrad Rieck [view email]<br>[v1]<br>Thu, 21 May 2026 14:47:54 UTC (11 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard, by Sahar Abdelnabi and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CR

next >

new<br>recent<br>| 2026-05

Change to browse by:

cs<br>cs.AI

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?)

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?)