corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0871d-c5a8-73e0-8539-5dfd8e5b3f2b

When an AI Evaluation Became a Cyber Intrusion

antomon.github.io · published 28 July 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at antomon.github.io Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
45
Words captured
23,209

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
OpenAI and Hugging Face partner to address security incident during model evaluation Read at the source ↗
openai.com
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident Read at the source ↗
huggingface.co
https://jfrog.com/blog/jfrog-and-openai-collaboration-on-zero-day-security-findings/
jfrog.com
https://doi.org/10.48550/arXiv.2605.11086
doi.org
Security incident disclosure — July 2026 Read at the source ↗
huggingface.co
https://www.reuters.com/business/openais-rogue-agent-compromised-an-account-second-tech-firm-sources-say-2026-07-28/
reuters.com
https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/
reuters.com
https://eur-lex.europa.eu/eli/reg/2024/1689/oj
eur-lex.europa.eu
https://doi.org/10.6028/NIST.AI.100-1
doi.org
https://doi.org/10.17351/ests2019.260
doi.org
https://nsarchive.gwu.edu/document/21440-document-44
nsarchive.gwu.edu
https://attack.mitre.org/matrices/enterprise/
attack.mitre.org
https://doi.org/10.6028/NIST.SP.800-218
doi.org
https://doi.org/10.6028/NIST.SP.800-218A
doi.org
https://doi.org/10.6028/NIST.SP.800-207
doi.org
https://doi.org/10.6028/NIST.SP.800-204D
doi.org
https://slsa.dev/spec/v1.2/
slsa.dev
https://doi.org/10.6028/NIST.CSWP.29
doi.org
https://doi.org/10.6028/NIST.SP.800-61r3
doi.org
https://www.iso.org/standard/72311.html
iso.org
https://www.first.org/global/sigs/vulnerability-coordination/multiparty/guidelines-v1-1
first.org
https://www.cisa.gov/resources-tools/resources/establishing-coordinated-vulnerability-disclosure-program-work-security-researchers
cisa.gov
https://doi.org/10.6028/NIST.AI.600-1
doi.org
https://kubernetes.io/docs/concepts/security/rbac-good-practices/
kubernetes.io
https://docs.aws.amazon.com/eks/latest/best-practices/identity-and-access-management.html
docs.aws.amazon.com
https://kubernetes.io/docs/concepts/security/pod-security-standards/
kubernetes.io
https://kubernetes.io/docs/concepts/services-networking/network-policies/
kubernetes.io
https://www.anthropic.com/research/discovering-cryptographic-weaknesses
anthropic.com
https://anthropic.com/document/hawk_key_recovery.pdf
anthropic.com
https://anthropic.com/document/aes_mobius_bridge.pdf
anthropic.com
https://doi.org/10.48550/arXiv.2607.18538
doi.org
https://leaderboard.far.ai/docs/report.pdf
leaderboard.far.ai
https://www.anthropic.com/research/many-shot-jailbreaking
anthropic.com
https://doi.org/10.48550/arXiv.2602.15001
doi.org
https://doi.org/10.48550/arXiv.2605.00267
doi.org
https://www.anthropic.com/news/disrupting-AI-espionage
anthropic.com
Improving instruction hierarchy in frontier LLMs Read at the source ↗
openai.com
https://www.anthropic.com/research/constitutional-classifiers
anthropic.com
https://alignment.anthropic.com/2026/backdooring-classifiers/
alignment.anthropic.com
https://www.pacingthefrontier.com/
pacingthefrontier.com
https://images.nvidia.com/pdf/Open-Weights-and-American-AI-Leadership.pdf
images.nvidia.com
https://x.com/JensenHuang/status/2080643682408321103
x.com
https://www.ntia.gov/programs-and-initiatives/artificial-intelligence/open-model-weights-report
ntia.gov
https://internationalaisafetyreport.org/publication/international-ai-safety-report-2026
internationalaisafetyreport.org
Investigating three real-world incidents in our cybersecurity evaluations Read at the source ↗
anthropic.com