Monthly publications
Paper types
defense 126
attack 34
survey 7
benchmark 6
tool 2
Domains
nlp 97
vision 70
multimodal 12
graph 11
federated-learning 9
generative 8
tabular 6
audio 2
reinforcement-learning 1
Co-occurring categories
Other OWASP categories that appear on the same papers
LLM10 Model Theft
58 ML09 Output Integrity Attack
8 LLM06 Sensitive Information Disclosure
7 ML10 Model Poisoning
5 ML03 Model Inversion Attack
5 ML01 Input Manipulation Attack
4 ML04 Membership Inference Attack
4 LLM01 Prompt Injection
3 ML06 AI Supply Chain Attacks
2 ML07 Transfer Learning Attack
2 LLM08 Excessive Agency
1 LS08 Reverse Engineering
1 ML02 Data Poisoning Attack
1 LS05 Triage & Prioritization
1 LS06 Red-Team Agents
1Top cited papers
142434445363738392102
MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
2025 benchmark
HoneypotNet: Backdoor Attacks Against Model Extraction
2025 defense
Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
2025 attack
Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
2025 benchmark
DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
2026 defense
Are Robust LLM Fingerprints Adversarially Robust?
2025 attack
Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluation
2025 defense
Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
2025 defense
TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone
2025 defense
$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
2025 attack