arXiv (OAI Expanded)
open access
SPARK: Representation-Level KV Memory Alignment for Safer Vision-Language Models
Vision-language models (VLMs) remain vulnerable to jailbreaks that distribute harmful intent across text and images, making unimodal safety mechanisms insufficient. We investigate whether this vulnerability can be mitigated directly in the multimodal key-value (KV) memory formed during prefill, with
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
- SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models#820996
- Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models#926208
- ShareGPT4Video/ShareGPT4Video#786796
- Multi-Image Visual Token Pruning in Large Visual Language Models#820643
- Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment#1142145
Record · ID 1083715
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