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/mcgill-nlp/adversarialtriggers
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/metallurk/local_gradients_smoothing
Local Gradients Smoothing: Defense against localized adversarial attacks
https://github.com/microsoft/distance-learner
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/mikepatel/Text-2-Image-GAN
https://github.com/minicheshire/InResNet
https://github.com/mohith-sakthivel/mine-pytorch
https://github.com/mrStasSmirnoff/GAN_basics
https://github.com/mshane911/NRP
Local Gradients Smoothing: Defense against localized adversarial attacks
https://github.com/ndb796/pytorch-adversarial-training-cifar
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/ndb796/test2
https://github.com/nicholasma88/CS260Final
ADef: an Iterative Algorithm to Construct Adversarial Deformations
https://github.com/nmcdermo/AdvML
https://github.com/nmndeep/robust-segmentation
https://github.com/nonparametric-adversarial/nonparametric
https://github.com/nura-j/attack_fl
https://github.com/nutellamok/advrush
Theoretically Principled Trade-off between Robustness and Accuracy
https://github.com/openai/cleverhans
https://github.com/optimization-for-data-driven-science/dair
Theoretically Principled Trade-off between Robustness and Accuracy
https://github.com/oskyhn/CNNs-Without-Borders
https://github.com/osu-nlp-group/amplegcg
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/parameterlab/trap
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/peck94/cann-detector
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/persistz/derivative-free-attack
https://github.com/pku-ml/pat
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/prakashpandey9/Text2Image-PyTorch
https://github.com/pralab/secml
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
https://github.com/princeton-sysml/jailbreak_llm
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/priscillalui/StackGAN-Stories
https://github.com/psandovalsegura/pytorch-gd-uap
Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations
https://github.com/radiant0726/cbw
https://github.com/rafiahmed40/stack-adverserial-network
https://github.com/rain152/PAT
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/realcrane/Defending-Black-box-Skeleton-based-Human-Activity-Classifiers
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
https://github.com/realcrane/robustactionrecogniser
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
https://github.com/reds-lab/narcissus
Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.