Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Ampere-Maxwell's Law: Problem-Solving01:17

Ampere-Maxwell's Law: Problem-Solving

513
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
513
Ampere's Law: Problem-Solving01:31

Ampere's Law: Problem-Solving

3.5K
Ampere's law states that for any closed looped path, the line integral of the magnetic field along the path equals the vacuum permeability times the current enclosed in the loop. If the fingers of the right hand curl along the direction of the integration path, the current in the direction of the thumb is considered positive. The current opposite to the thumb direction is considered negative.
Specific steps need to be considered while calculating the symmetric magnetic field distribution...
3.5K
Non-ohmic Devices00:51

Non-ohmic Devices

1.0K
In most substances, the current flow is proportional to the voltage applied to it. A simple relationship between the values of current, voltage, and resistance is known as Ohm's law. Nonohmic devices do not exhibit a linear relationship between voltage and current. One such device is the semiconducting circuit element known as a diode. A diode is a circuit device that allows current flow in only one direction.
Consider a simple circuit consisting of a battery, a diode, and a resistor. A...
1.0K
BIBO stability of continuous and discrete -time systems01:24

BIBO stability of continuous and discrete -time systems

327
System stability is a fundamental concept in signal processing, often assessed using convolution. For a system to be considered bounded-input bounded-output (BIBO) stable, any bounded input signal must produce a bounded output signal. A bounded input signal is one where the modulus does not exceed a certain constant at any point in time.
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system....
327
Interference and Decay01:16

Interference and Decay

104
Forgetting is a complex cognitive phenomenon influenced by several factors, among which interference and decay are particularly prominent. These processes explain why individuals often struggle to retrieve specific information from memory, leading to lapses in recall that can be observed in everyday situations.
Interference occurs when competing memories hinder the retrieval of particular information. It can be classified into two types: proactive and retroactive interference. Proactive...
104
Characteristics of OpAmp01:17

Characteristics of OpAmp

502
The operational amplifier, commonly known as an op-amp, is a specially designed electronic circuit component. Its purpose is to work in conjunction with other circuit elements to execute a defined signal-processing operation. Consider an equivalent circuit model of an op-amp, as depicted in Figure 1; the output section comprises a voltage-controlled source in parallel with the output resistance Ro.
502

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Supernetwork-based efficient mapping of deep learning applications to mixed-precision hardware using model adaptation.

Nature communications·2026
Same author

Analogue speech recognition based on physical computing.

Nature·2025
Same author

Training of physical neural networks.

Nature·2025
Same author

The growing memristor industry.

Nature·2025
Same author

Rapid learning with phase-change memory-based in-memory computing through learning-to-learn.

Nature communications·2025
Same author

Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing.

Nature computational science·2025

Related Experiment Video

Updated: May 27, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

7.7K

The inherent adversarial robustness of analog in-memory computing.

Corey Lammie1, Julian Büchel2, Athanasios Vasilopoulos2

  • 1IBM Research Europe, Rüschlikon, Switzerland. corey.lammie@ibm.com.

Nature Communications
|February 19, 2025
PubMed
Summary
This summary is machine-generated.

Analog in-memory computing chips enhance deep neural network robustness against adversarial attacks. This study experimentally validates that inherent noise in these systems provides significant defense for image classification and natural language processing tasks.

More Related Videos

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx
09:49

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx

Published on: May 13, 2020

4.0K
Gradient Echo Quantum Memory in Warm Atomic Vapor
10:00

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

12.8K

Related Experiment Videos

Last Updated: May 27, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

7.7K
In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx
09:49

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx

Published on: May 13, 2020

4.0K
Gradient Echo Quantum Memory in Warm Atomic Vapor
10:00

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

12.8K

Area of Science:

  • Computer Science
  • Electrical Engineering
  • Materials Science

Background:

  • Deep neural networks (DNNs) are vulnerable to adversarial attacks, posing security risks.
  • Analog in-memory computing (AIMC) substrates, utilizing devices like phase change memory (PCM), are theorized to offer inherent adversarial robustness.
  • Experimental validation of AIMC's adversarial robustness for DNN inference is lacking.

Purpose of the Study:

  • To experimentally validate the adversarial robustness of DNN inference on an AIMC chip.
  • To investigate the sources and impact of noise on adversarial robustness in AIMC systems.
  • To assess the robustness of larger transformer networks on AIMC for natural language processing (NLP) tasks.

Main Methods:

  • Implementation of an image classification DNN on a PCM-based AIMC chip.
  • Evaluation of adversarial robustness against various attack types, including hardware-in-the-loop (HITL) attacks.
  • Analysis of stochastic noise sources (recurrent and non-recurrent) contributing to robustness.
  • Simulation of a transformer network for NLP tasks on AIMC.

Main Results:

  • The AIMC chip demonstrated significantly higher adversarial robustness compared to conventional methods for image classification.
  • HITL attacks also showed reduced effectiveness, indicating hardware-level defense.
  • Stochastic noise sources were identified as the primary contributors to adversarial robustness, with their characteristics significantly influencing the defense.
  • Simulations confirmed continued robustness for larger transformer networks in NLP tasks.

Conclusions:

  • Analog in-memory computing, particularly PCM-based systems, offers a promising hardware-based solution for enhancing DNN adversarial robustness.
  • The inherent stochastic noise in AIMC is crucial for this defense mechanism.
  • AIMC is a viable substrate for robust AI inference across different network architectures and tasks.