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/locuslab/convex_adversarial
공식 코드Provable defenses against adversarial examples via the convex outer adversarial polytope
https://github.com/locuslab/projected_sinkhorn
공식 코드Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
https://github.com/lok-18/a2rnet
공식 코드A2RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion
https://github.com/lokender/REGroup
공식 코드REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions
https://github.com/lovelyqian/styleadv-cdfsl
공식 코드StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning
https://github.com/luck1y/beamattack
공식 코드Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack
https://github.com/luyg45/hardnoboxattack
공식 코드https://github.com/lzalza/linbp
공식 코드A Theoretical View of Linear Backpropagation and Its Convergence
https://github.com/machanic/MetaAdvDet
공식 코드MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
https://github.com/magic-ma-tech/dfb
공식 코드DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack
https://github.com/magnetar-iiith/pril
공식 코드How Private Is Your RL Policy? An Inverse RL Based Analysis Framework
https://github.com/mahmoudkanazzal/minta
공식 코드Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detection
https://github.com/mahossam/Explain2Attack
공식 코드Explain2Attack: Text Adversarial Attacks via Cross-Domain Interpretability
https://github.com/mahya-ahmadi/neurounlock
공식 코드NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks
https://github.com/mahyarnajibi/FreeAdversarialTraining
공식 코드https://github.com/maoubo/unidoor
공식 코드UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
https://github.com/marcoarmenta/hidden-activations-are-not-enough
공식 코드Hidden Activations Are Not Enough: A General Approach to Neural Network Predictions
https://github.com/martin-ochoa/foobar
공식 코드FooBaR: Fault Fooling Backdoor Attack on Neural Network Training
https://github.com/masoudhashemi/PermuteAttack
공식 코드PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards
https://github.com/matouskozak/amg
공식 코드Combining Generators of Adversarial Malware Examples to Increase Evasion Rate
https://github.com/matthewcym/same
공식 코드https://github.com/mattswatson/attack-agnostic-adversarial-attack-detection
공식 코드Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
https://github.com/max-andr/square-attack
공식 코드Square Attack: a query-efficient black-box adversarial attack via random search
https://github.com/maxproto/iba
공식 코드https://github.com/mazurowski-lab/intrinsic-properties
공식 코드https://github.com/mdbloice/Patch-Augmentation
공식 코드Patch augmentation: Towards efficient decision boundaries for neural networks
https://github.com/meet-cjli/ctrl
공식 코드An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
https://github.com/meettyj/recipe2vec
공식 코드Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks
https://github.com/megum1/beagle
공식 코드BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
https://github.com/megum1/lotus
공식 코드LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
https://github.com/mehrdadsaberi/watermark_robustness
공식 코드Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
https://github.com/metaphors/TSAttack
공식 코드TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
https://github.com/mingjiewang0606/lcye-attack_reid
공식 코드Look Closer to Your Enemy: Learning to Attack via Teacher-Student Mimicking
https://github.com/mingzelucasni/fba
공식 코드Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process
https://github.com/minliu01/non-adversarial_backdoor
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.