Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from EDBT 2026 / reviewers in the wild / expert

Hongsen Lang

dblp:432/6614 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
1since 2021 · last 2026
0009-0000-5416-0315ORCID · reported

Domains — the database's venue-derived domains; a paper can count in several

Databases, data management, data science and information retrieval · 1 · 1 since 2021Applied, interdisciplinary, general and emerging computing · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Network and information security
1 paper
Security and privacy of machine learning · 100%
Artificial intelligence
1 paper
Language models and text generation · 100%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Language models and text generation
LLM agents		 1.012026
Beyond Detection: Autonomous Anomaly Remediation for MCP Against Tool Poisoning Attacks · WWW 2026
Security and privacy of machine learning › large language model security
LLM agent security		 1.012026
Beyond Detection: Autonomous Anomaly Remediation for MCP Against Tool Poisoning Attacks · WWW 2026
Security and privacy of machine learning › prompt injection
tool poisoning attack		 1.012026
Beyond Detection: Autonomous Anomaly Remediation for MCP Against Tool Poisoning Attacks · WWW 2026

Methods — techniques the papers use, named apart from their topics

autonomous remediation · 2.0anomaly detection · 2.0
YearPublicationVenuePosition
2026 Beyond Detection: Autonomous Anomaly Remediation for MCP Against Tool Poisoning Attacks
abstract
LLM-powered agents are evolving from passive recommenders into autonomous executors, leveraging tools via the Model Context Protocol (MCP) for web automation. However, this paradigm introduces a new vulnerability: tool poisoning attacks that manipulate the MCP context can corrupt an agent's reasoning. Existing methods focus on anomaly detection and lack autonomous correction mechanisms, hindering their real-world deployment.
Guanquan Shi, Yichao Gao, Hongsen Lang, Yunhao Yao, Haohua Du, Xiang-Yang Li 0001
 WWW5