Offense - Adversarial Threats/Attacks

Youtube search...

• Cybersecurity
• Defense - Anomaly Detection
• Capabilities

______________________________________________________

• Cleverhans - library for benchmarking the vulnerability of machine learning models to adversarial examples blog
• Adversarial Machine Learning for Anti-Malware Software | nababora @ GitHub
• Deep-pwning/Metasploit | Clarence Chio
• EvadeML.org | University of Virginia
• AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack
• Pattern Recognition and Applications Lab (PRA Lab)
  • AdversariaLib | PRA Lab
  • adversarial label flip attacks against Support Vector Machines (ALFASVMLib) | PRA Lab

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. Myth: An attacker must have access to the model to generate adversarial examples. Fact: Adversarial examples generalize across models trained to perform the same task, even if those models have different architectures and were trained on a different training set. This means an attacker can train their own model, generate adversarial examples against it, and then deploy those adversarial examples against a model they do not have access to. -Deep Learning Adversarial Examples – Clarifying Misconceptions | Goodfellow et al.

Sources

Xu et al. Automatically Evading Classifiers: A Case Study on PDF Malware Classifiers

Kantchelian et al. Evasion and Hardening of Tree Ensemble Classifiers

Ororbia II et al. Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization

Jin et al. Robust Convolutional Neural Networks under Adversarial Noise

Barreno et al. Can Machine Learning Be Secure?

J.D. Tygar, Ling Huang et al. Adversarial Machine Learning

Xiao et al. Adversarial and Secure Machine Learning

Uther et al.Adversarial Reinforcement Learning

Kurakin et al. Adversarial examples in the physical world

Laskov et al. Machine Learning in Adversarial Environments

W/ Papers

Biggio et al. Poisoning Attacks against Support Vector Machines, 25 Mar 2013

Biggio et al. Support Vector Machines Under Adversarial Label Noise, 2011

Eykholt et al. Robust Physical-World Attacks on Deep Learning Visual Classification

Naveiro et al. Adversarial classification: An adversarial risk analysis approach, 21 Feb 2018

Kantarcioglu et al. Adversarial Data Mining for Cyber Security, 28 Oct 2016

Al-Dujaili et al. Adversarial Deep Learning for Robust Detection of Binary Encoded Malware, 25 Mar 2018

Grosse et al. Adversarial Examples for Malware Detection, 12 Aug 2017

Grosse et al. Adversarial Perturbations Against Deep Neural Networks for Malware Classification, 16 Jun 2016

Kreuk et al. Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples, 13 May 2018

Keshet et al. Adversarial Examples on Discrete Sequences for Beating Whole-Binary Malware Detection, 13 Feb 2018

Goodfellow et al.Adversarial Examples that Fool both Human and Computer Vision, 22 May 2018

Goodfellow et al. Explaining and Harnessing Adversarial Examples, 20 Mar 2015

Goodfellow et al. Intriguing properties of neural networks, 19 Feb 2014

Yuan et al. Adversarial Examples. Attacks and Defenses for Deep Learning, 5 Jan 2018

Miller et al. Adversarial Learning. A Critical Review and Active Learning Study, 27 May 2017

Kolosnjaji et al. Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables, 12 Mar 2018

Chen et al. Automated Poisoning Attacks and Defenses in Malware Detection Systems: An Adversarial Machine Learning Approach, 31 Oct 2017

Nguyen et al. Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images, 2 Apr 2015

Papernot et al. Adversarial Perturbations Against Deep Neural Networks, 16 Jun 2016

Papernot et al. Adversarial Examples in Machine Learning, 1 Feb 2017

Papernot et al. Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks, 14 Nov 2015

Uesato et al. Adversarial Risk and the Dangers of Evaluating Against Weak Attacks, 12 Jun 2018

Norton et al. Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning, 1 Aug 2017

Wang et al. Adversary Resistant Deep Neural Networks with an Application to Malware Detection, 27 Apr 2017

Stokes et al. Attack and Defense of Dynamic Analysis-Based, Adversarial Neural Malware Classification Models, 16 Dec 2017

Goodfellow et al. Attacking Machine Learning with Adversarial Examples, 24 Feb 2017

Carlini et al. Adversarial Examples: Targeted Attacks on Speech-to-Text, 5 Jan 2018

Shen et al. AUROR: Defending Against Poisoning Attacks in Collaborative Deep Learning Systems, 5 Dec 2016

Hosseini et al. Blocking Transferability of Adversarial Examples in Black-Box Learning Systems, 13 Mar 2017

Raghunathan et al. Certified Defenses against Adversarial Examples, 29 Jan 2018

Rouhani et al. CuRTAIL: ChaRacterizing and Thwarting AdversarIal deep Learning, 1 Apr 2018

Paudice et al. Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection, 8 Feb 2018

Chen et al. EAD. Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples, 10 Feb 2018

Xu et al. Feature Squeezing; Detecting Adversarial Examples in Deep Neural Networks, 5 Dec 2017

Hu et al. Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN, 20 Feb 2017

Chen et al. Hardening Malware Detection Systems Against Cyber Maneuvers. An Adversarial Machine Learning Approach, 13 Oct 2017

Demontis et al. Infinity-Norm Support Vector Machines Against Adversarial Label Contamination, 2017

Abhijith Introduction to Artificial intelligence for security professionals, 12 Aug 2017

Anderson et al. Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning, 26 Jan 2018

Papernot et al. On the (Statistical) Detection of Adversarial Examples, 21 Feb 2017

Papernot et al. Practical Black-Box Attacks against Machine Learning, 8 Feb 2016

Papernot et al. The Limitations of Deep Learning in Adversarial Settings, 24 Nov 2015

Bulo et al. Randomized Prediction Games for Adversarial Machine Learning, 11 Nov 2017

Kantchelian Taming Evasions in Machine Learning Based Detection, 12 Aug 2016

Chen et al. Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning, 15 Dec 2017

Goodfellow et al. The Space of Transferable Adversarial Examples, 23 May 2017

Akhtar et al. Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey, 26 Feb 2018

Abramson, Myriam Toward Adversarial Online Learning and the Science of Deceptive Machines, 13 Sep 2017

Madry et al. Towards Deep Learning Models Resistant to Adversarial Attacks, 19 Jun 2017

Luo et al. Towards Imperceptible and Robust Adversarial Example Attacks against Neural, 15 Jan 2018

Muñoz-González et al. Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization, 29 Aug 2017

Goodfellow et al. Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples, 24 May 2016

Weaponizing Machine Learning

Youtube search...