Adversarial Attack

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1776–1800 of 1808 papers

Title	Date	Tasks	Status	Hype
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples	Feb 1, 2018	Adversarial AttackAdversarial Defense	CodeCode Available	0
Certified Defenses against Adversarial Examples	Jan 29, 2018	Adversarial AttackAdversarial Defense	CodeCode Available	0
Deflecting Adversarial Attacks with Pixel Deflection	Jan 26, 2018	Adversarial Attack	CodeCode Available	0
Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations	Jan 24, 2018	Adversarial AttackDepth Estimation	CodeCode Available	1
Query-Efficient Black-box Adversarial Examples (superceded)	Dec 19, 2017	Adversarial Attack	CodeCode Available	0
Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser	Dec 8, 2017	Adversarial AttackAdversarial Defense	CodeCode Available	0
Model Extraction Warning in MLaaS Paradigm	Nov 20, 2017	Adversarial AttackBIG-bench Machine Learning	—Unverified	0
Linear system security -- detection and correction of adversarial attacks in the noise-free case	Nov 15, 2017	Adversarial Attack	—Unverified	0
Provable defenses against adversarial examples via the convex outer adversarial polytope	Nov 2, 2017	Adversarial Attack	CodeCode Available	0
Generating Natural Adversarial Examples	Oct 31, 2017	Adversarial Attackimage-classification	CodeCode Available	0
Boosting Adversarial Attacks with Momentum	Oct 17, 2017	Adversarial Attack	CodeCode Available	0
Standard detectors aren't (currently) fooled by physical adversarial stop signs	Oct 9, 2017	Adversarial Attack	—Unverified	0
Resilient Learning-Based Control for Synchronization of Passive Multi-Agent Systems under Attack	Sep 28, 2017	Adversarial Attack	—Unverified	0
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples	Sep 13, 2017	Adversarial AttackAdversarial Robustness	CodeCode Available	0
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models	Aug 14, 2017	Adversarial AttackAdversarial Defense	CodeCode Available	0
Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words	Aug 1, 2017	Adversarial AttackHate Speech Detection	—Unverified	0
Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning	Aug 1, 2017	Adversarial AttackAdversarial Defense	CodeCode Available	0
Foolbox: A Python toolbox to benchmark the robustness of machine learning models	Jul 13, 2017	Adversarial AttackBIG-bench Machine Learning	CodeCode Available	2
Towards Deep Learning Models Resistant to Adversarial Attacks	Jun 19, 2017	Adversarial AttackAdversarial Defense	CodeCode Available	1
Adversarial and Clean Data Are Not Twins	Apr 17, 2017	Adversarial Attack	CodeCode Available	0
Biologically inspired protection of deep networks from adversarial attacks	Mar 27, 2017	Adversarial AttackSecond-order methods	—Unverified	0
Adversarial Examples for Semantic Segmentation and Object Detection	Mar 24, 2017	Adversarial Attackimage-classification	CodeCode Available	1
Tactics of Adversarial Attack on Deep Reinforcement Learning Agents	Mar 8, 2017	Adversarial AttackAtari Games	—Unverified	0
On Detecting Adversarial Perturbations	Feb 14, 2017	Adversarial AttackBinary Classification	CodeCode Available	0
Adversarial Images for Variational Autoencoders	Dec 1, 2016	Adversarial Attack	CodeCode Available	0

Show:10 25 50

← PrevPage 72 of 73Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet20	Test Accuracy	89.95	89.95(1)	Community Verified
2	Xu et al.	Attack: PGD20	78.68	—	Unverified
3	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
4	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
5	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
6	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
7	XU-Net	Robust Accuracy	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	51.28	—	Unverified
2	multi-resolution self-ensembles	Attack: AutoAttack	47.85	—	Unverified