Pith. sign in

Manipulating multimodal agents via cross-modal prompt injection

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 2

years

2026 2

roles

background 1

polarities

background 1

representative citing papers

Security in LLM-as-a-Judge: A Comprehensive SoK

cs.CR · 2026-03-31 · accept · novelty 8.0

The first SoK on LLM-as-a-Judge security organizes attacks targeting judges, attacks using judges, defenses leveraging judges, and security-domain applications while flagging vulnerabilities.

citing papers explorer

Showing 2 of 2 citing papers.

  • Security in LLM-as-a-Judge: A Comprehensive SoK cs.CR · 2026-03-31 · accept · none · ref 52

    The first SoK on LLM-as-a-Judge security organizes attacks targeting judges, attacks using judges, defenses leveraging judges, and security-domain applications while flagging vulnerabilities.

  • WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections cs.CR · 2026-05-14 · unverdicted · none · ref 59

    WARD is a guard model trained on 177K web samples and adversarially hardened via attacker-guard co-evolution to achieve high recall on prompt injections with low false positives and no added latency.