Monthly publications
Paper types
attack 178
defense 118
benchmark 22
survey 17
tool 2
Domains
nlp 168
vision 161
federated-learning 52
multimodal 51
generative 21
reinforcement-learning 18
graph 13
timeseries 8
audio 5
tabular 3
Co-occurring categories
Other OWASP categories that appear on the same papers
ML02 Data Poisoning Attack
67 LLM01 Prompt Injection
27 ML07 Transfer Learning Attack
23 ML06 AI Supply Chain Attacks
17 LLM03 Training Data Poisoning
14 ML01 Input Manipulation Attack
13 LLM08 Excessive Agency
6 ML05 Model Theft
5 ML03 Model Inversion Attack
4 ML04 Membership Inference Attack
3 ML09 Output Integrity Attack
3 LLM04 Model Denial of Service
3 LLM06 Sensitive Information Disclosure
2 ML08 Model Skewing
2 LLM07 Insecure Plugin Design
1Top cited papers
132227310485767768595104
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
2025 attack
A Survey of Secure Semantic Communications
2025 survey
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
2025 attack
Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
2025 defense
Dynamic Black-box Backdoor Attacks on IoT Sensory Data
2025 attack
DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
2025 attack
BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
2025 attack
Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects
2025 attack
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
2025 defense
HoneypotNet: Backdoor Attacks Against Model Extraction
2025 defense