Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception

arXiv 2604.20895•45ce0b1884c1dc1310357a16b1d1b30569e7c153587a1b2579b49b2177f263a8
DNN-limitationsISO-26262ISO/SAE-21434LLM-agentsLLM-safetyRAGSDN-intrusion-detection','keystroke-inference','VR-securitySafeRedirectadaptive-defenseagentic-modelsarxiv-source-leakageautonomous-drivingdata-leakagedata-poisoningfunction-callingfunction-hijackinginternal-safety-collapseinterpretability-attacksjailbreakingmembership-inferenceretrieval-augmented-generationrisk-assessmentsecurity-recall-divergencesensitivity-uncertainty-alignmentuncertainty-calibration

Paper metadata

arXiv ID
2604.20895
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
45ce0b1884c1dc1310357a16b1d1b30569e7c153587a1b2579b49b2177f263a8
Enrichment time
2026-04-24T07:23:36Z
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.

Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception · Baitaphish