ML09
Output Integrity Attack
Manipulating ML model outputs and predictions
742 papers Browse all papers
Monthly publications
Paper types
defense 478
benchmark 128
tool 60
attack 59
survey 17
Domains
vision 476
generative 282
nlp 224
multimodal 125
audio 110
tabular 5
reinforcement-learning 3
federated-learning 3
graph 3
timeseries 1
Co-occurring categories
Other OWASP categories that appear on the same papers
ML01 Input Manipulation Attack
22 LLM01 Prompt Injection
11 ML02 Data Poisoning Attack
9 ML05 Model Theft
8 LLM08 Excessive Agency
6 ML10 Model Poisoning
3 LLM07 Insecure Plugin Design
2 LLM10 Model Theft
2 ML04 Membership Inference Attack
2 LLM06 Sensitive Information Disclosure
2 ML07 Transfer Learning Attack
1 ML03 Model Inversion Attack
1Top cited papers
1102939465665758595105
FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
2025 defense
Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection
2025 defense
SynthID-Image: Image watermarking at internet scale
2025 tool
Towards Interactive Deepfake Analysis
2025 tool
Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
2025 defense
T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
2025 defense
RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
2025 defense
State-of-the-art AI-based Learning Approaches for Deepfake Generation and Detection, Analyzing Opportunities, Threading through Pros, Cons, and Future Prospects
2025 survey
AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
2025 defense
Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
2025 defense