conftrace_

preference manipulation

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

location hiding (1) attack stealthiness (1) information elicitation (1) search engine (1) model context protocol (1) preference hijacking (1) content ranking (1) multi-agent system (1) large language model (1) image perturbation (1)

Papers

MPMA: Preference Manipulation Attack Against Model Context Protocol AAAI 2026 Adversarial Search Engine Optimization for Large Language Models ICLR 2025 Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time EMNLP 2025 The Surprising Power of Hiding Information in Facility Location AAAI 2020