Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior
arXiv 2607.15286•ee88bd1b324d6e4255acc12d253856caef6234dde4d577e76140764d255580a9
5g-side-channeladversarial-imagesautomated-exploit-generationchain-of-thoughtcyber-deceptionfederated-learningfhejailbreak-transferllm-jailbreakmedical-imagingmemory-poisoningmodel-safetymultimodal-securitysmart-contract-exploitationspeech-backdoor
Paper metadata
- arXiv ID
- 2607.15286
- 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
- ee88bd1b324d6e4255acc12d253856caef6234dde4d577e76140764d255580a9
- Enrichment time
- 2026-07-20T07:23:40Z
- 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.