Monthly publications
Paper types
attack 33
benchmark 14
tool 12
defense 3
survey 1
Domains
nlp 62
multimodal 3
vision 2
tabular 1
audio 1
generative 1
reinforcement-learning 1
Co-occurring categories
Other OWASP categories that appear on the same papers
LLM01 Prompt Injection
57 LS10 Benchmarks & Evaluation
34 LLM08 Excessive Agency
12 ML01 Input Manipulation Attack
7 LLM07 Insecure Plugin Design
5 LS01 Vulnerability Discovery
4 LS02 Exploit Generation
3 LS07 Blue-Team Agents
2 ML04 Membership Inference Attack
2 LLM06 Sensitive Information Disclosure
2 ML10 Model Poisoning
1 LLM03 Training Data Poisoning
1 LS09 Fuzzing & Test Generation
1 LS03 Reconnaissance & OSINT
1 LS04 Patch & Remediation
1 ML05 Model Theft
1 LS05 Triage & Prioritization
1 ML03 Model Inversion Attack
1Top cited papers
192634435362728291101
RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
2025 attack
Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
2025 attack
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
2026 tool
Diffusion LLMs are Natural Adversaries for any LLM
2025 attack
Takedown: How It's Done in Modern Coding Agent Exploits
2025 attack
Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
2025 benchmark
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
2025 attack
Anecdoctoring: Automated Red-Teaming Across Language and Place
2025 attack
RedTWIZ: Diverse LLM Red Teaming via Adaptive Attack Planning
2025 tool
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
2025 tool