A Non-Line-of-Sight, Multi-Modality-based Side-Channel IP Theft Attack on Additive Manufacturing Using Dual Smartphones
2026-07-02T07:23:31Z•6b9391f3a394d3fcb360759cf87172039f98704ab1a47ae6b2caf77157a3b99c
3d printingIIoT intrusion detection`,`provenance`,`forensicsMoAIRAGacoustic emissionsadditive manufacturingattack surfacebackdoorblack-box poisoningblocklacefederationfunction-calling LLMsintellectual property theftjailbreakmagnetic emissionsmobile agentsmobile sensorson-device AIpoisoningprivacy-preserving protocolsreasoning-level attacksretrieval-augmented generationside-channelsimulated moderation tracesvision-language models
What happened
Collection of recent arXiv submissions highlighting emergent security risks across AI/ML-enabled systems and adjacent domains. Key contributions include: a practical non-line-of-sight side-channel IP-theft attack on 3D printers using two smartphones (high fidelity G-code reconstruction); a privacy-preserving Federated Sovereign Transport Protocol for tamper-evident, confined inter-node messaging; new attack surfaces and concrete exploits against third-party mobile agents powered by VLMs (including privilege‑free arbitrary command execution); ReShift, a stealthy reasoning-level backdoor method对
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_cr
- Record identifier
- 6b9391f3a394d3fcb360759cf87172039f98704ab1a47ae6b2caf77157a3b99c
- Enrichment time
- 2026-07-02T07:23:31Z
- 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.