Papers with Code 아카이브

Adversarial Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 4
평가표: 3
보존된 평가 기록: 9

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/sj21j/Regularized_Relaxation

공식 코드

Adversarial Attacks on Large Language Models Using Regularized Relaxation

https://github.com/skoffas/going-in-style

공식 코드

Going In Style: Audio Backdoors Through Stylistic Transformations

https://github.com/skp1999/SMAB

공식 코드

SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation

https://github.com/slkdfjslkjfd/fl_fairness_attacks

공식 코드

Attacks on fairness in Federated Learning

https://github.com/smaityumich/individual-fairness-testing

공식 코드

Statistical inference for individual fairness

https://github.com/smartcameras/ColorFool

공식 코드

ColorFool: Semantic Adversarial Colorization

https://github.com/smartcameras/RP-FGSM

공식 코드

Exploiting vulnerabilities of deep neural networks for privacy protection

https://github.com/sohaib730/argos-adversarial_detection

공식 코드

Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency

https://github.com/spandan-madan/in_distribution_adversarial_examples

공식 코드

In-distribution adversarial attacks on object recognition models using gradient-free search

https://github.com/spaxilia/recover-triggered-states

공식 코드

Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning

https://github.com/srijankr/petgen

공식 코드

PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification Models

https://github.com/sssadrizadeh/NMT_Obfuscator

공식 코드

NMT-Obfuscator Attack: Ignore a sentence in translation with only one word

https://github.com/sssadrizadeh/act

공식 코드

A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation

https://github.com/sssadrizadeh/nmt-targeted-attack

공식 코드

Targeted Adversarial Attacks against Neural Machine Translation

https://github.com/sssadrizadeh/transfool

공식 코드

TransFool: An Adversarial Attack against Neural Machine Translation Models

https://github.com/sssadrizadeh/transformer-text-classifier-attack

공식 코드

Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers

https://github.com/stanislavfort/ensemble-everything-everywhere

공식 코드

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

https://github.com/stanislavfort/multi-attacks

공식 코드

Multi-attacks: Many images $+$ the same adversarial attack $\to$ many target labels

https://github.com/stars-cs/black_box_traffic

공식 코드

Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models

https://github.com/stellargraph/stellargraph

공식 코드

Adversarial Examples on Graph Data: Deep Insights into Attack and Defense

https://github.com/steven202/semantic_adv_via_dm

공식 코드

Semantic Adversarial Attacks via Diffusion Models

https://github.com/stoliktomer/saga

공식 코드

SAGA: Spectral Adversarial Geometric Attack on 3D Meshes

https://github.com/stratosphereips/meme_malware_rl

공식 코드

The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning

https://github.com/sunblaze-ucb/transferability-advdnn-pub

공식 코드

Delving into Transferable Adversarial Examples and Black-box Attacks

https://github.com/sunh1113/efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios

공식 코드

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

https://github.com/sunwoolee0504/wall

공식 코드

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

https://github.com/superrrpotato/Defending-Neural-Backdoors-via-Generative-Distribution-Modeling

공식 코드

Defending Neural Backdoors via Generative Distribution Modeling

https://github.com/suzhigangssz/avih

공식 코드

Hiding Visual Information via Obfuscating Adversarial Perturbations

https://github.com/t-maho/SurFree

공식 코드

SurFree: a fast surrogate-free black-box attack

https://github.com/tabacof/adv_vae

공식 코드

Adversarial Images for Variational Autoencoders

https://github.com/tensorflow/cleverhans

공식 코드

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

https://github.com/thanhtrunghuynh93/fastfedul

공식 코드

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience

https://github.com/thu-bpm/cwba

공식 코드

Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution

https://github.com/thu-ml/ares

공식 코드

Adversarial Attacks on ML Defense Models Competition

https://github.com/thunlp/HiddenKiller

공식 코드

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

https://github.com/thunlp/NeuBA

공식 코드

Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.