Monthly publications
Paper types
defense 460
attack 435
benchmark 235
survey 48
tool 45
Domains
nlp 1180
multimodal 273
vision 192
generative 49
audio 24
reinforcement-learning 23
graph 5
federated-learning 2
Co-occurring categories
Other OWASP categories that appear on the same papers
ML01 Input Manipulation Attack
233 LLM08 Excessive Agency
169 LLM07 Insecure Plugin Design
73 LLM06 Sensitive Information Disclosure
62 ML07 Transfer Learning Attack
45 ML02 Data Poisoning Attack
27 ML10 Model Poisoning
27 ML06 AI Supply Chain Attacks
15 ML09 Output Integrity Attack
11 ML04 Membership Inference Attack
5 ML03 Model Inversion Attack
5 LLM03 Training Data Poisoning
4 ML05 Model Theft
3 LLM04 Model Denial of Service
3 LLM10 Model Theft
1Top cited papers
1392343114105106107108999109
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
2025 defense
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
2025 benchmark
A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
2025 defense
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
2026 defense
TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
2025 defense
Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
2025 survey
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
2025 attack
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
2025 attack
RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
2025 attack
Defending Against Prompt Injection with DataFilter
2025 defense