Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors

Feb 11, 2021
Pooya Tavallali, Vahid Behzadan, Peyman Tavallali, Mukesh Singhal

* 15 pages 

  Access Paper or Ask Questions

Adversarial Attacks on Deep Algorithmic Trading Policies

Oct 22, 2020
Yaser Faghan, Nancirose Piazza, Vahid Behzadan, Ali Fathi

* 17 pages - under submission 

  Access Paper or Ask Questions

Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification

Sep 01, 2020
Bibek Upadhayay, Vahid Behzadan

* Under review at IEEE ISI '20 

  Access Paper or Ask Questions

Founding The Domain of AI Forensics

Dec 11, 2019
Ibrahim Baggili, Vahid Behzadan

* Accepted for presentation at SafeAI2020 

  Access Paper or Ask Questions

A Novel Approach for Detection and Ranking of Trendy and Emerging Cyber Threat Events in Twitter Streams

Jul 12, 2019
Avishek Bose, Vahid Behzadan, Carlos Aguirre, William H. Hsu

* 9 pages, 3 figures, and 5 tables 

  Access Paper or Ask Questions

Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies

Jun 03, 2019
Vahid Behzadan, William Hsu


  Access Paper or Ask Questions

Adversarial Exploitation of Policy Imitation

Jun 03, 2019
Vahid Behzadan, William Hsu


  Access Paper or Ask Questions

Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)

Jun 03, 2019
Vahid Behzadan, William Hsu


  Access Paper or Ask Questions

RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies

Jun 03, 2019
Vahid Behzadan, William Hsu


  Access Paper or Ask Questions

TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles

Nov 14, 2018
Vahid Behzadan, James Minton, Arslan Munir


  Access Paper or Ask Questions

Emergence of Addictive Behaviors in Reinforcement Learning Agents

Nov 14, 2018
Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir


  Access Paper or Ask Questions

The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning

Oct 23, 2018
Vahid Behzadan, Arslan Munir

* arXiv admin note: text overlap with arXiv:1807.06064, arXiv:1712.03632, arXiv:1803.02811, arXiv:1710.00814 by other authors 

  Access Paper or Ask Questions

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

Jun 27, 2018
Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, Patrick McDaniel

* Technical report for https://github.com/tensorflow/cleverhans 

  Access Paper or Ask Questions

Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise

Jun 04, 2018
Vahid Behzadan, Arslan Munir

* arXiv admin note: substantial text overlap with arXiv:1701.04143, arXiv:1712.09344 

  Access Paper or Ask Questions

Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles

Jun 04, 2018
Vahid Behzadan, Arslan Munir


  Access Paper or Ask Questions

A Psychopathological Approach to Safety Engineering in AI and AGI

May 23, 2018
Vahid Behzadan, Arslan Munir, Roman V. Yampolskiy


  Access Paper or Ask Questions

Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger

Dec 23, 2017
Vahid Behzadan, Arslan Munir

* arXiv admin note: text overlap with arXiv:1701.04143 

  Access Paper or Ask Questions

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Jan 16, 2017
Vahid Behzadan, Arslan Munir

* 14 pages, 5 figures, pre-print of submission to MLDM '17 

  Access Paper or Ask Questions