arXiv AI
EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
3d ago
Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
The paper introduces Counterfactual Neighborhood Risk Fields (CNRF), an evidence‑grounded framework that improves safety for vision‑language models (VLMs). CNRF builds context‑matched benign‑harmful counterfactual pairs, uses their representation differences to define risk directions, and separates neighborhood support from risk estimation. This approach allows selective intervention rather than blanket rejection, achieving high macro defense success rates across multiple VLMs while preserving benign‑task utility.
arXiv AI
Oct 7
From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models
arXiv:2610.07514v1 Announce Type: new Abstract: A vision-language model may need to combine an image with a prompt to recognize a safety risk that neither reveals alone. Where does this joint safety...
arXiv Computer Vision
Sep 22
A$^2$Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
A$^2$Safe is a framework for safe and effective Visual Question Answering that aligns counterfactual evidence with adaptive agent collaboration. It uses a Grounded Safety Evidence Board to make safety decisions explicit, enforcing invariance to safety‑irrelevant changes while allowing appropriate transitions when risk‑critical evidence changes. The system achieves a 95.72 SIUO safety score, reduces benign refusals on MOSSBench to 14.67%, and maintains a 78.34 average VQA score with 27.8% token overhead.
arXiv AI
Sep 10
Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails
The paper introduces Mind2Web-Injection, a benchmark of 9,954 instruction‑screenshot pairs designed to evaluate whether vision‑language models (VLMs) use visual evidence when judging conflicts between on‑screen text and user instructions. Across six VLMs, models with similar overall precision can differ dramatically in Evidence‑Aligned Detection (EAD), revealing that verdict‑only metrics miss critical grounding failures. The authors also propose two training‑free interventions—ReadGate and CmdCompare—to improve evidence grounding and instruction‑command consistency, and argue for separate reporting of verdict correctness, evidence localization, and counterfactual responsiveness.
arXiv AI
Jul 2
EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards
arXiv:2607. 00218v1 Announce Type: cross Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories.
arXiv AI
Jul 28
AI-generated Images Challenge Visual Trust in High-risk Scenarios
arXiv:2607. 22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation.