arXiv (All)
open access
Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally
A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to generate freely, produces the original, correct description with no trace of the target. We call this dissociation the
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
- Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally#1181691
- PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models#303213
- STAMP – saliency targeted adversarial mask perturbation: A localized targeted attack on vision-language models#355654
- Images Amplify Misinformation Sharing in Vision-Language Models#177061
- One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models#1130943
Record · ID 1188123
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