Monthly publications
Paper types
defense 104
benchmark 68
attack 49
survey 26
tool 11
Domains
nlp 253
multimodal 51
vision 12
reinforcement-learning 12
graph 4
audio 3
generative 1
Co-occurring categories
Other OWASP categories that appear on the same papers
LLM01 Prompt Injection
198 LLM07 Insecure Plugin Design
55 LS10 Benchmarks & Evaluation
18 LS06 Red-Team Agents
12 LS07 Blue-Team Agents
10 ML01 Input Manipulation Attack
9 LLM06 Sensitive Information Disclosure
8 ML06 AI Supply Chain Attacks
8 ML10 Model Poisoning
8 ML09 Output Integrity Attack
6 ML02 Data Poisoning Attack
5 LS01 Vulnerability Discovery
2 ML07 Transfer Learning Attack
2 LS02 Exploit Generation
1 LS09 Fuzzing & Test Generation
1 LS04 Patch & Remediation
1 ML08 Model Skewing
1 ML05 Model Theft
1Top cited papers
167211310485868778797106
Agentic Misalignment: How LLMs Could Be Insider Threats
2025 benchmark
A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
2025 defense
Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
2025 survey
A Survey on Agentic Security: Applications, Threats and Defenses
2025 survey
Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
2025 survey
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
2025 survey
Securing AI Agent Execution
2025 defense
BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
2025 defense
Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents
2026 defense
Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
2025 defense