When Models Take Shortcuts: The causes of shortcut learning in neural networks
Adversarial Attacks

When Models Take Shortcuts: The causes of shortcut learning in neural networks

Neuroscientists once thought they could train rats to navigate mazes by color. Rats don’t perceive colors at all. Instead, they rely on the distinct odors of different colors of paint. New work finds that neural networks are prone to this sort of misalignment between training goals and learning.

June 3, 20202 min read
Undercover Networks: Protecting neural networks from differential power analysis
Adversarial Attacks

Undercover Networks: Protecting neural networks from differential power analysis

Neural networks can spill their secrets to those who know how to ask. A new approach secures them from prying eyes. Researchers demonstrate that that adversaries can find out a model’s parameter values by measuring its power use.

May 13, 20202 min read
Undercover Networks: Protecting neural networks from differential power analysis
Adversarial Attacks

Undercover Networks: Protecting neural networks from differential power analysis

Neural networks can spill their secrets to those who know how to ask. A new approach secures them from prying eyes. Researchers demonstrate that that adversaries can find out a model’s parameter values by measuring its power use.

May 13, 20202 min read
Phantom Menace: Fake images can fool some self-driving cars.
Adversarial Attacks

Phantom Menace: Fake images can fool some self-driving cars.

Some self-driving cars can’t tell the difference between a person in the roadway and an image projected on the street. A team of researchers used projectors to trick semiautonomous vehicles into detecting people, road signs, and lane markings that didn’t exist.

February 12, 20202 min read
Phantom Menace: Fake images can fool some self-driving cars.
Adversarial Attacks

Phantom Menace: Fake images can fool some self-driving cars.

Some self-driving cars can’t tell the difference between a person in the roadway and an image projected on the street. A team of researchers used projectors to trick semiautonomous vehicles into detecting people, road signs, and lane markings that didn’t exist.

February 12, 20202 min read
Bias Goes Undercover: Adversarial attacks can fool explainable AI techniques.
Adversarial Attacks

Bias Goes Undercover: Adversarial attacks can fool explainable AI techniques.

As black-box algorithms like neural networks find their way into high-stakes fields such as transportation, healthcare, and finance, researchers have developed techniques to help explain models’ decisions. New findings show that some of these methods can be fooled.

November 27, 20192 min read
Bias Goes Undercover: Adversarial attacks can fool explainable AI techniques.
Adversarial Attacks

Bias Goes Undercover: Adversarial attacks can fool explainable AI techniques.

As black-box algorithms like neural networks find their way into high-stakes fields such as transportation, healthcare, and finance, researchers have developed techniques to help explain models’ decisions. New findings show that some of these methods can be fooled.

November 27, 20192 min read
Anonymous Faces
Adversarial Attacks

Anonymous Faces

A number of countries restrict commercial use of personal data without consent unless they’re fully anonymized. A new paper proposes a way to anonymize images of faces, purportedly without degrading their usefulness in applications that rely on face recognition.

October 2, 20192 min read
Anonymous Faces
Adversarial Attacks

Anonymous Faces

A number of countries restrict commercial use of personal data without consent unless they’re fully anonymized. A new paper proposes a way to anonymize images of faces, purportedly without degrading their usefulness in applications that rely on face recognition.

October 2, 20192 min read
This Shirt Hates Surveillance
Adversarial Attacks

This Shirt Hates Surveillance

Automatic license plate readers capture thousands of vehicle IDs each minute, allowing law enforcement and private businesses to track drivers with or without their explicit consent.

August 21, 20191 min read
This Shirt Hates Surveillance
Adversarial Attacks

This Shirt Hates Surveillance

Automatic license plate readers capture thousands of vehicle IDs each minute, allowing law enforcement and private businesses to track drivers with or without their explicit consent.

August 21, 20191 min read

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox