ML Security Papers

ML06

AI Supply Chain Attacks

Compromising ML through dependencies and third-party components

47 papers Browse all papers

Monthly publications

Paper types

attack 18

defense 12

survey 8

tool 5

benchmark 4

Domains

nlp 28

vision 10

multimodal 5

generative 4

reinforcement-learning 3

federated-learning 2

Co-occurring categories

Other OWASP categories that appear on the same papers

ML10 Model Poisoning

LLM01 Prompt Injection

LLM07 Insecure Plugin Design

LLM08 Excessive Agency

ML02 Data Poisoning Attack

ML05 Model Theft

LLM03 Training Data Poisoning

LLM06 Sensitive Information Disclosure

ML04 Membership Inference Attack

Top cited papers

MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem

Sentry: Authenticating Machine Learning Artifacts on the Fly

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study

Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis

FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems

HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Browse all 47 papers