mlsanityData to 14 Oct 2026

Out of Sight: Compression-Aware Content Protection against Agentic Crawlers

arXiv 2607.08180 ↗First posted 9 Jul 2026cs.CR cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 2 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 63 references that are in the map. First posted on arXiv 9 Jul 2026.

Builds on

32 of 63 references.

References · 32

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  6. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  7. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  8. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  9. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
  10. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 483
  11. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  12. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
20 more
  1. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  2. 2023Adapting Language Models to Compress Contextscited by 356
  3. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 348
  4. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  5. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 215
  6. 2025Prompt Injection Attack to Tool Selection in LLM Agentscited by 158
  7. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 146
  8. 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 132
  9. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbationscited by 65
  10. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 64
  11. 2023Compressed Context Memory For Online Language Model Interactioncited by 43
  12. 2024Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detectioncited by 29
  13. 2024Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystackcited by 19
  14. 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planningcited by 14
  15. 2024Enhancing Training Data Attribution for Large Language Models with Fitting Error Considerationcited by 7
  16. 2025Scrapers selectively respect robots.txt directives: evidence from a large-scale empirical studycited by 6
  17. 2024Evil twins are not that evil: Qualitative insights into machine-generated promptscited by 5
  18. 2025CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistancecited by 5
  19. 2024Towards Operationalizing Right to Data Protectioncited by 3
  20. 2025Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Modelscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Signal-Driven Observation for Long-Horizon Web Agents
  2. 2026Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
  3. 2026Prismata: Confining Cross-Site Prompt Injection in Web Agents
  4. 2026Untrusted Content Masking for Web Agents with Security Guarantees
  5. 2025FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents
  6. 2026Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
  7. 2024ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
  8. 2026Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents