Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Sign inBecome a Member
Home/Research Paper Library/Practical Black-Box Attacks against Machine Learning

Practical Black-Box Attacks against Machine Learning

Showed that adversarial examples can be crafted against a black-box model by training a local substitute and exploiting transferability, establishing the query-only threat model for ML APIs.

black-box attackstransferabilityml apis

Research question

Can an attacker with only query access craft adversarial examples for a remote model?

Key findings

  • A substitute model trained on the target's labels yields transferable adversarial examples - Attacks succeeded against MetaMind, Amazon and Google classifiers with few queries

Sources

PreviousCommunication-Efficient Learning of Deep Networks from Decentralized DataNextModel Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit researchReport a correction or request removal

Related in Research Paper Library

The More It Says, the More You Pay: A Black-Box Audit of Provider-Side Token Inflation in LLM Services

In pay-per-token LLM services, the more a model says, the more users pay. Dishonest providers can covertly manipulate generation to inflate output tokens while largely preserving task utility. We define such…

Adversarial examples and evasion2026

A GAN-Based Framework for Robust DDoS Attack Detection

The availability and consistency of online services remain vulnerable due to Distributed Denial of Service (DDoS) attacks. These attacks are evolving by adopting more complex strategies to evade traditional network…

Adversarial examples and evasion2026

When Agents Look Like Beacons: NIDS Evasion by Model Context Protocol Traffic

The Model Context Protocol (MCP) standardizes communication between autonomous Artificial Intelligence (AI) agents and remote tools over Streamable HTTP. This shift introduces a class of machine-generated,…

Adversarial examples and evasion2026