arXiv CS
open access
SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models
Activation steering offers an inference-time defense for vision--language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, protection on benchmark inputs may not persist across alternative expressions of the same harmful request. We investigate t
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
- SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models#1144084
- Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning#819692
- Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning#809696
- Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives#1064302
- FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making#822124
Record · ID 1136777
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