E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
arXiv 2605.00955•a5032f2e47a95065df79df27f3e4fbc505ca866ffdd7520b632c8428f0b361b0
PUFadaptive-unlearningblack-box-attacksconfidence-signalsdefensive-prompt-injectione-miaembedding-defenseshallucination-suppressionjailbreakingllm-jailbreakmachine-unlearningmembership-inferencemulti-agent-systemspost-quantum-cryptographyprivacy-leakageprompt-sanitizationragslopsquattingsoftware-supply-chainsonarsrtjtc-um iaterminal-fingerprintingtracewebassembly-attestation
Paper metadata
- arXiv ID
- 2605.00955
- 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
- a5032f2e47a95065df79df27f3e4fbc505ca866ffdd7520b632c8428f0b361b0
- Enrichment time
- 2026-05-05T07:23:39Z
- 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.