Skip to content
Oct 12 · Monday

All papers

Found 1 paper
Filter5

Impact

Unauthorized actions6Output manipulation1

System type

Models and APIs43LLM applications11AI Agent26web agent1Multi-agent systems5Embodied systems and robotics3

System component

Memory0Vision1Embeddings0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Impact：Output manipulationSystem type：web agentSystem component：MemorySystem component：VisionSystem component：EmbeddingsClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2603.16960

    Adversarial attacks against modern vision-language models

    Conduct adversarial attacks on product images for open-source visual shopping agents and induce wrong purchases

    arXiv
    2603.16960
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    LLaVA-v1.5-7B, Qwen2.5-VL-7B
    AbstractThe authors state that LLaVA is easily induced by three attacks to buy the wrong item, while Qwen's correct purchase rate remains close to its clean condition.

    The authors compare the robustness of two open-source VLM shopping agents against image adversarial perturbations in a self-built e-commerce environment.

    Paper analysisRead analysis
You have reached the end