Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
arXiv 2605.02900•ac4fe7042191a26cac5c4f8cc08eaa8a2b242fce6bd04fc89137a7172abf43d7
FreeUpSALOSoKadaptive-authenticationadversarial-attacksanomaly-detectionbackdoor-attackscontrastive-privacyembodied-aiencrypted-trafficfinancial-securityfrequency-decouplingintrusion-detection-system','LiteShield'','lightweight-IDS'','biiotjailbreak-detectionmultimodal-perceptionpost-quantum-tlspq-tlsprivacy-sanitizationrepresentation-engineeringrisk-cost-modelrobust-planningsafetytls-observabilityweb-tracker-detection
Paper metadata
- arXiv ID
- 2605.02900
- 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
- ac4fe7042191a26cac5c4f8cc08eaa8a2b242fce6bd04fc89137a7172abf43d7
- Enrichment time
- 2026-05-06T07:23:40Z
- 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.