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/Intriguing properties of neural networks

Intriguing properties of neural networks

The paper that discovered adversarial examples: tiny optimised perturbations that make image classifiers fail and transfer between models, launching the field of adversarial machine learning.

adversarial examplesfoundationalcomputer vision

Research question

Are deep networks stable to small, imperceptible input perturbations?

Key findings

  • Imperceptible perturbations found by optimisation flip classifications reliably - The same perturbations transfer across models trained on different data - Individual units are no more semantically meaningful than random directions in activation space

Sources

PreviousExplaining and Harnessing Adversarial ExamplesNextPoisoning Attacks against Support Vector Machines

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