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

Reinforcement01:23

Reinforcement

360
Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
360
Randomized Experiments01:13

Randomized Experiments

7.9K
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
7.9K
Associative Learning01:27

Associative Learning

612
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
612
Observational Learning01:12

Observational Learning

329
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
329
Dynamic Equilibrium02:20

Dynamic Equilibrium

53.7K
A reversible chemical reaction represents a chemical process that proceeds in both forward (left to right) and reverse (right to left) directions. When the rates of the forward and reverse reactions are equal, the concentrations of the reactant and product species remain constant over time and the system is at equilibrium. A special double arrow is used to emphasize the reversible nature of the reaction. The relative concentrations of reactants and products in equilibrium systems vary greatly;...
53.7K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

1.9K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.9K

You might also read

Related Articles

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

Sort by
Same author

Mixed infection with <i>Burkholderia cepacia</i> and <i>Cutibacterium acnes</i> following subarachnoid hemorrhage surgery: a case report.

Frontiers in medicine·2026
Same author

Collision-Free Coordination of Heterogeneous Multiagent Systems Under Independent DoS Attacks.

IEEE transactions on cybernetics·2026
Same author

TWEAK Receptor Promotes Vascular Remodeling in Hypertension by Activating Autophagy.

Journal of the American Heart Association·2026
Same author

Cold-induced liver dysfunction drives cardiac damage through a liver-heart axis.

European journal of pharmacology·2026
Same author

A Nanoliposome Platform Co-Delivery of Hydroxypinacolone Retinoate and Carnosine for Enhanced Epidermal/Dermal Delivery and Multi-Functional Anti-Aging Efficacy.

Pharmaceutics·2026
Same author

Advancing In-Context Learning for Efficient and Stable Medical Report Generation.

IEEE transactions on pattern analysis and machine intelligence·2026

Related Experiment Video

Updated: Sep 22, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

604

Adversarial Robustness of Deep Reinforcement Learning Based Dynamic Recommender Systems.

Siyu Wang1, Yuanjiang Cao1, Xiaocong Chen1

  • 1School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia.

Frontiers in Big Data
|May 20, 2022
PubMed
Summary

This study explores adversarial attacks on reinforcement learning (RL) recommendation systems. Findings show strategically timed attacks are effective, even at lower frequencies, and a detector generalizes across attack types.

Keywords:
adversarial attackdeep learning—artificial neural network (DL-ANN)deep reinforcement learning (deep RL)recommender systems (RS)robustness

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

694

Related Experiment Videos

Last Updated: Sep 22, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

604
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

694

Area of Science:

  • Machine Learning
  • Deep Learning
  • Reinforcement Learning
  • Causality

Background:

  • Adversarial attacks, including input perturbations and adversarial samples, challenge machine learning and deep learning systems, particularly interactive recommendation systems.
  • The latent embedding space in these systems complicates early detection of adversarial attacks.
  • Counterfactual causality offers a method for generating adversarial samples distinct from training data distributions.

Purpose of the Study:

  • To investigate adversarial examples and develop attack-agnostic detection methods for reinforcement learning (RL)-based interactive recommendation systems.
  • To understand the impact of attack strength and frequency on adversarial performance.
  • To evaluate the generalization capability of a deep learning-based detector against various adversarial crafting methods.

Main Methods:

  • Crafting diverse adversarial examples through input perturbations and causal factor interventions.
  • Augmenting recommendation systems with a deep learning classifier for attack detection using crafted data.
  • Evaluating model performance on standard datasets, analyzing attack strength, frequency, and timing.

Main Results:

  • Most adversarial attacks were found to be effective, with both strength and frequency significantly impacting performance.
  • Strategically timed attacks achieved comparable performance using only 1/3 to 1/2 the attack frequency of other methods.
  • A white-box detector trained on one crafting method demonstrated generalization to several other crafting methods.

Conclusions:

  • Adversarial attacks pose a significant threat to RL-based recommendation systems, but their effectiveness can be modulated by timing and frequency.
  • Deep learning-based detection models can generalize across different adversarial crafting techniques, offering a robust defense.
  • Further research into causal inference can inform the generation and detection of sophisticated adversarial examples.