arXiv AI
Jul 17
Pretraining Data Can Be Poisoned through Computational Propaganda
arXiv:2607. 15267v1 Announce Type: new Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate.
Identifying AI Web Scrapers Using Canary Tokens
The paper introduces a method to detect which web scrapers feed data to large language models (LLMs) by deploying dynamic websites that issue unique canary tokens to each scraper. By querying LLMs for information about these sites, the authors can identify when an LLM consistently outputs the unique tokens, indicating exposure to a specific scraper. Experiments on 22 production LLM systems show the technique reliably uncovers both known and undisclosed scrapers, offering a tool for third parties to monitor and control unwanted web scraping.
Related stories
Hugging Face Trending Papers
Oct 25
LLM WikiLeaks: Uncovering URL-Based Capability Extension and Security Circumvention in Agentic Message Boards
Autonomous agents have been observed acting beyond their assigned tasks, accessing unauthorized systems, and establishing communication channels to exchange information, yet the Web and network-level...
arXiv AI
Oct 27
LLM WikiLeaks: Uncovering URL-Based Capability Extension and Security Circumvention in Agentic Message Boards
arXiv:2610.34542v1 Announce Type: cross Abstract: Autonomous agents have been observed acting beyond their assigned tasks, accessing unauthorized systems, and establishing communication channels to e...
arXiv AI
Oct 27
Proof-of-Agentness: Towards Verifying Agents on the Web
arXiv:2610.35288v1 Announce Type: new Abstract: CAPTCHAs and bot detection have helped protect Web services from automated abuse for decades by distinguishing humans from bots. However, the emergence...
arXiv AI
Oct 28
DeGenTWeb: A First Look at MGT-dominant Websites
DeGenTWeb is a system that identifies websites whose informational prose is largely machine‑generated text (MGT) with minimal human input. By adapting MGT detectors for web pages and aggregating results across sites, the study reports that 20.9% of Common Crawl‑archived sites (Jan–Jul 2026) and 13.6% of Bing‑linked sites (2025) are MGT‑dominant, with a 0.12% mislabeling rate for human‑authored sites. The prevalence of MGT‑dominant sites is increasing over time and many share the same owner.
arXiv Computation and Language
2d ago
When 200 OK Is Not an Answer: Silent Fetch Failures in Agentic Web Content Acquisition
The study investigates how often web agents incorrectly treat an HTTP 200 response as a successful fetch of useful content. By sampling 10,307 URLs—including random paths and expert‑verified claim citations—the authors found that roughly 20–25% of 200 responses lack the page’s main content, leading to inflated estimates of claim verifiability and citation drift. They propose simple heuristics and classifiers to detect unusable responses, achieving high recall with low false‑alarm rates, and recommend that agents report fetch outcomes explicitly.
arXiv AI
Sep 1
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
arXiv:2605.29224v2 Announce Type: replace-cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incor...
arXiv AI
Sep 10
Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
arXiv:2609.06027v1 Announce Type: cross Abstract: Search-augmented LLM agents are increasingly used for consumer decisions, making them vulnerable to Generative Engine Optimization (GEO) poisoning. E...
arXiv Computation and Language
Sep 1
FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents
arXiv:2510.03204v2 Announce Type: replace Abstract: Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens...
arXiv AI
Jul 10
Prismata: Confining Cross-Site Prompt Injection in Web Agents
arXiv:2607. 08147v1 Announce Type: cross Abstract: Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces.
Hugging Face Trending Papers
Jun 17
Towards an Agent-First Web: Redesigning the Web for AI Agents
The World Wide Web was built on an assumption held for three decades: the primary consumer of web content is a human being. This permeates every layer; its access model presumes human visitors, its economics rest on human attention, and its content targets human perception.
arXiv AI
Jun 16
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
arXiv:2602. 09222v2 Announce Type: replace-cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf.