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/optml-group/qf-attack
공식 코드A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion
https://github.com/optml-group/red-adv
공식 코드Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
https://github.com/oryany12/DeSparsify-Adversarial-Attack
공식 코드DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers
https://github.com/pan-zihao/sca
공식 코드SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion
https://github.com/paoche11/gungnir
공식 코드Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
https://github.com/papamarkou/neurotron_experiments
공식 코드https://github.com/papercgba/cgba
공식 코드Claim-Guided Textual Backdoor Attack for Practical Applications
https://github.com/papermsucode/advhat
공식 코드AdvHat: Real-world adversarial attack on ArcFace Face ID system
https://github.com/paperspapers/badprompt
공식 코드https://github.com/pasalab/pga
공식 코드Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
https://github.com/pasquini-dario/OutDomainExamples
공식 코드https://github.com/paulaharder/SpectralAdversarialDefense
공식 코드SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain
https://github.com/pgao-lab/amga
공식 코드Towards Adaptive Meta-Gradient Adversarial Examples for Visual Tracking
https://github.com/pgg3/L-AutoDA
공식 코드L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
https://github.com/phantivia/t-pgd
공식 코드Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework
https://github.com/phd-taoliu/fcba
공식 코드Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning
https://github.com/phibenz/robustness_comparison_vit_mlp-mixer_cnn
공식 코드Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs
https://github.com/pku-ml/nlb
공식 코드https://github.com/plasmashen/BackdoorPTM
공식 코드https://github.com/plpl2019/tpa
공식 코드Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
https://github.com/poloclub/3D-Gaussian-Splat-Attack
공식 코드https://github.com/pralab/Fast-Minimum-Norm-FMN-Attack
공식 코드Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
https://github.com/psyker-team/mist-v2
공식 코드Targeted Attack Improves Protection against Unauthorized Diffusion Customization
https://github.com/qcznlp/uncertainty
공식 코드Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
https://github.com/qcznlp/uncertainty_attack
공식 코드Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
https://github.com/qilong-zhang/Patch-wise-iterative-attack
공식 코드https://github.com/qilong-zhang/Staircase-sign-method
공식 코드https://github.com/qilong-zhang/Targeted_Patch-wise-plusplus_iterative_attack
공식 코드https://github.com/qiulingxu/FeatureSpaceAttack
공식 코드https://github.com/qsx830/mixbridge
공식 코드MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
https://github.com/qsyao/attack_landmark_detection
공식 코드Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection
https://github.com/quocnsh/sepp
공식 코드SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text
https://github.com/quocnsh/votetrans
공식 코드VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations
https://github.com/rainavyas/img_attackability
공식 코드https://github.com/rainavyas/naacl-2022-residue-detector
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.