Papers with Code 아카이브
Adversarial Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/huangyebiaoke/adversarial-attack-method-based-on-IGA
공식 코드An Improved Genetic Algorithm and Its Application in Neural Network Adversarial Attack
https://github.com/huanranchen/Similar-Target-Attacker
공식 코드https://github.com/huanzhang12/ATLA_robust_RL
공식 코드Robust Reinforcement Learning on State Observations with Learned Optimal Adversary
https://github.com/huanzhang12/ZOO-Attack
공식 코드https://github.com/huawei-lin/InplaceOnlineGBDT
공식 코드Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data
https://github.com/huitailangyz/AITL
공식 코드Adaptive Image Transformations for Transfer-based Adversarial Attack
https://github.com/huyvnphan/eccv2022-ribac
공식 코드RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
https://github.com/hxxdtd/pund
공식 코드Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective
https://github.com/hxzhong1997/fsba
공식 코드https://github.com/hychaochao/chat-models-backdoor-attacking
공식 코드https://github.com/iCGY96/APR
공식 코드https://github.com/iamaaditya/pixel-deflection
공식 코드https://github.com/ibm/baddiffusion
공식 코드https://github.com/ibm/villandiffusion
공식 코드VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
https://github.com/iceli1007/DAT-GAN
공식 코드A New Perspective on Stabilizing GANs training: Direct Adversarial Training
https://github.com/ict-convergence-security-lab-chosun/sdba
공식 코드SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
https://github.com/id-fr/idfr
공식 코드Enhanced countering adversarial attacks via input denoising and feature restoring
https://github.com/idea-iitd/TANDIS
공식 코드Task and Model Agnostic Adversarial Attack on Graph Neural Networks
https://github.com/idrl-lab/Full-coverage-camouflage-adversarial-attack
공식 코드FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack
https://github.com/ifnspaml/advattackdet
공식 코드Detecting Adversarial Perturbations in Multi-Task Perception
https://github.com/imogenqi/SMA
공식 코드https://github.com/imrclab/flying_adversarial_patch
공식 코드Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches
https://github.com/in-dist-adversarials/in_distribution_adversarial_examples
공식 코드In-distribution adversarial attacks on object recognition models using gradient-free search
https://github.com/infolab-skku/singleclassadv
공식 코드Single-Class Target-Specific Attack against Interpretable Deep Learning Systems
https://github.com/ink-usc/bite
공식 코드BITE: Textual Backdoor Attacks with Iterative Trigger Injection
https://github.com/intelligent-computing-lab-yale/rate-vs-direct
공식 코드https://github.com/invisibilitee/invisibilitee
공식 코드InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee
https://github.com/invisibletriggerdiffusion/invisible_triggers_for_diffusion
공식 코드https://github.com/itailang/geometric_adv
공식 코드Geometric Adversarial Attacks and Defenses on 3D Point Clouds
https://github.com/jaiprakash1824/vlm_adv_attack
공식 코드https://github.com/janzahalka/trainwreck
공식 코드Trainwreck: A damaging adversarial attack on image classifiers
https://github.com/javirandor/wdr
공식 코드"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks
https://github.com/jbeomlee93/AdvCAM
공식 코드Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
https://github.com/jcroh0508/flats
공식 코드Robust Smart Home Face Recognition under Starving Federated Data
https://github.com/jcroh0508/msdt
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.