ML01
Input Manipulation Attack
Adversarial examples and evasion attacks on ML models
839 papers Browse all papers
Monthly publications
Paper types
attack 376
defense 338
benchmark 85
survey 26
tool 14
Domains
vision 558
nlp 306
multimodal 215
generative 55
audio 43
graph 33
tabular 27
reinforcement-learning 26
timeseries 16
federated-learning 14
Co-occurring categories
Other OWASP categories that appear on the same papers
LLM01 Prompt Injection
233 ML02 Data Poisoning Attack
25 ML09 Output Integrity Attack
22 ML10 Model Poisoning
13 LLM08 Excessive Agency
6 ML03 Model Inversion Attack
4 ML04 Membership Inference Attack
4 LLM04 Model Denial of Service
4 ML05 Model Theft
4 LLM06 Sensitive Information Disclosure
3 LLM07 Insecure Plugin Design
1 ML08 Model Skewing
1Top cited papers
1342273124105968778696106
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
2025 benchmark
A Survey of Secure Semantic Communications
2025 survey
AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs
2025 benchmark
Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
2025 attack
Parameter Interpolation Adversarial Training for Robust Image Classification
2025 defense
Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models
2025 attack
Rerouting LLM Routers
2025 attack
Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
2025 attack
Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
2025 attack
GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
2025 defense