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/Zoky-2020/Set-level_Guidance_Attack
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/a1600012888/YOPO-You-Only-Propagate-Once
https://github.com/aayushmanace/patchalign24
Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation
https://github.com/abahram77/mnistChallenge
https://github.com/abahram77/mnist_challenge
https://github.com/abstractteen/antiforgery
https://github.com/adnansirajrakin/T-BFA
https://github.com/adverML/SAMMD
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
https://github.com/aelnouby/Text-to-Image-Synthesis
https://github.com/ai-secure/adversarial-glue
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
https://github.com/akshaymehra24/poisoning_certified_defenses
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
https://github.com/alankarj/robust_nlp
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
https://github.com/albertmillan/adversarial-training-pytorch
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/alexalemi/vib_demo
https://github.com/alvarorobledo/fyp-foolbox
Foolbox: A Python toolbox to benchmark the robustness of machine learning models
https://github.com/amanb2000/magic_words
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/amerch/CIFAR100-Training
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/anandaltekar/movie-poster-generator
https://github.com/andrewilyas/ens-adv-train-attack
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/andreysorokin/scam-net
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
https://github.com/anirudh9784/Adversarial-Defense
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks
https://github.com/anishathalye/Guided-Denoise
Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
https://github.com/anishathalye/pixel-deflection
https://github.com/anonymousjack/hijacking
Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking
https://github.com/anwu1219/Marabou
Efficient Neural Network Analysis with Sum-of-Infeasibilities
https://github.com/aprincemohamed/data-driven-adversarial-amc
Data-Driven Subsampling in the Presence of an Adversarial Actor
https://github.com/arobey1/advbench
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/arobey1/mbrdl
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/arobey1/smooth-llm
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/as791/Adversarial-Example-Attack-and-Defense
https://github.com/as791/ZOO_Attack_PyTorch
https://github.com/avrahamraviv/formal-verification-of-object-detection
https://github.com/azshue/boosting_robust
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
https://github.com/batuceng/max_quantile
https://github.com/bboylyg/NAD
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.