Search papers, labs, and topics across Lattice.
This paper introduces CAPE, a novel framework designed to protect high-value textual content from LLM-based agents by injecting invisible perturbations that induce significant information loss during the agents' context compression processes. By leveraging a surrogate compressor to generate disruptive seed perturbations and adapting them through a guided evolution process, CAPE achieves up to 75.8% more information loss compared to existing defenses while maintaining the visual integrity of the content. The framework's effectiveness is validated across multiple content types and compression settings, demonstrating its applicability in real-world scenarios such as LangGraph and GitHub Copilot.
Invisible perturbations can lead to a staggering 75.8% information loss in agentic crawlers without altering the human-visible content.
The rise of LLM-based agents with reasoning, summarization, and memory capabilities has created a new threat surface for online content that conventional defenses fail to address. Existing defenses like access controls can be circumvented by agents mimicking ordinary browsers, and injection-based defenses often degrade human readability. In this paper, we revisit the agent pipeline and identify context compression, which agents routinely invoke to fit context budgets, as a critical yet overlooked defense layer. We propose CAPE, a framework that protects high-value textual content by injecting invisible perturbations without changing its human-visible surface form, thereby inducing severe information loss during agent compression. CAPE extracts disruptive seed perturbations from an accessible surrogate compressor, then adapts them to query-only target compressors through prior-guided evolution and preference-calibrated candidate prioritization, achieving effective protection under a low query budget. Experiments on three content types and four compression settings show that CAPE improves information loss by up to 75.8% over the strongest baseline while keeping protected content visually indistinguishable from originals. CAPE also transfers to real-world settings, including the LangGraph agent workflow and GitHub Copilot, highlighting its generality and practical value. This paper aims to reveal context compression as a new defense layer, promoting content protection research in the agent era.
