MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning

arXiv 2605.26154•2d840d0e623d0bd93f84f55e0d0d9686f35bf7cf6d1c1076e0afdaee3dbe29b8
DDoS detectionIDSIoT securityLLM securityOS sandboxRAGSDNSandlockadversarial attacksagent securityautonomybenchmarksdifferential privacyjailbreakmemory poisoningmetric differential privacymodel evaluationprompt injectionsafety engineeringsandboxingself-evolving agentstool hijacking

Paper metadata

arXiv ID
2605.26154
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
2d840d0e623d0bd93f84f55e0d0d9686f35bf7cf6d1c1076e0afdaee3dbe29b8
Enrichment time
2026-05-27T07:23:30Z
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.