# ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation

arXiv: https://arxiv.org/abs/2412.21123 · HTML: https://mlsanity.com/paper/2412.21123/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 52 of its 75 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 30 of 52)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity](https://mlsanity.com/paper/2305.13169/) (2023)
- [MedDialog: Two Large-scale Medical Dialogue Datasets](https://mlsanity.com/paper/2004.03329/) (2020)
- [EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage](https://mlsanity.com/paper/2409.11295/) (2024)
- [Reconstructing Training Data with Informed Adversaries](https://mlsanity.com/paper/2201.04845/) (2022)
- [The Privacy Onion Effect: Memorization is Relative](https://mlsanity.com/paper/2206.10469/) (2022)
- [Adversarial Examples Make Strong Poisons](https://mlsanity.com/paper/2106.10807/) (2021)
- [Foundation Models and Fair Use](https://mlsanity.com/paper/2303.15715/) (2023)

## Built on by (most cited first, 3 of 3)

- [Throttling Web Agents Using Reasoning Gates](https://mlsanity.com/paper/2509.01619/) (2025)
- [TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text](https://mlsanity.com/paper/2607.28862/) (2026)
- [VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents](https://mlsanity.com/paper/2609.38270/) (2026)

## Abstract (arXiv)

As large language models increasingly memorize web-scraped training content, they risk exposing copyrighted or private information. Existing protections require compliance from crawlers or model developers, fundamentally limiting their effectiveness. We propose ExpShield, a proactive self-guard that mitigates memorization while maintaining readability via invisible perturbations, and we formulate it as a constrained optimization problem. Due to the lack of an individual-level risk metric for natural text, we first propose instance exploitation, a metric that measures how much training on a specific text increases the chance of guessing that text from a set of candidates-with zero indicating perfect defense. Directly solving the problem is infeasible for defenders without sufficient knowledge, thus we develop two effective proxy solutions: single-level optimization and synthetic perturbation. To enhance the defense, we reveal and verify the memorization trigger hypothesis, which can help to identify key tokens for memorization. Leveraging this insight, we design targeted perturbations that (i) neutralize inherent trigger tokens to reduce memorization and (ii) introduce artificial trigger tokens to misdirect model memorization. Experiments validate our defense across attacks, model scales, and tasks in language and vision-to-language modeling. Even with privacy backdoor, the Membership Inference Attack (MIA) AUC drops from 0.95 to 0.55 under the defense, and the instance exploitation approaches zero. This suggests that compared to the ideal no-misuse scenario, the risk of exposing a text instance remains nearly unchanged despite its inclusion in the training data.