Out of Sight: Compression-Aware Content Protection against Agentic Crawlers
Xuefei Wang
cs.CR, cs.AI
Submitted: 2026-07-09
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
Abstract
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.
Sources
- Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
- In-context Autoencoder for Context Compression in a Large Language Model
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
- Prompt Injection Attack to Tool Selection in LLM Agents
- AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
- Understanding the Ability of LLMs to Handle Character-Level Perturbation
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation
- Data Poisoning in Deep Learning: A Survey
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs