arXiv (All)
open access
Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric
Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over model behavior. Among them, the evil persona vector is particularly relevant to understanding harmful behavior, jailbreak vulnerabilities, and the unlea
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling#224431
- Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition#246428
- CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation#1036182
- CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation#1006783
- Robustness of Vision Language Models Against Split-Image Harmful Input Attacks#798765
Record · ID 1343081
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive