Enabling Adversarial Robustness in AI Models through Kubeflow MLOps
arXiv 2605.15249•823fd6d6f5aba02ec6a72b00b1bcd8aeeeb0060e582ab5e3add1880852254b01
adversarial-mladversarial-trainingagentic-systemsdifferential-privacydp-sgdfgsmkubeflowkubernetesllm-securitymemory-poisoningmicroarchitectural-attacksmicroservicesmlopsopacusowasp-top-10','autonomous-testing'pgdpoc-generationprime+probeprivacy-leakageprivilege-escalationprogram-analysisprompt-injectionretrieval-augmented-llmsecurity-testingspectre
Paper metadata
- arXiv ID
- 2605.15249
- Version
- Not specified by this published record
- Category
- Computer Science — Cryptography and Security (cs.CR)
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
Evidence and limitations
- Source ID
- arxiv_cs_cr
- Record identifier
- 823fd6d6f5aba02ec6a72b00b1bcd8aeeeb0060e582ab5e3add1880852254b01
- Enrichment time
- 2026-05-18T07:23:31Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.