Papers with Code 아카이브
Adversarial Robustness
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 7
- 보존된 평가 기록
- 33
Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yuancheng-xu/dynamics-aware-robust-training
공식 코드Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
https://github.com/yumozi/guard
공식 코드Towards Adversarially Robust Dataset Distillation by Curvature Regularization
https://github.com/yundaqwe/ultimate-combo
공식 코드The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations
https://github.com/yunqing-me/attackvlm
공식 코드On Evaluating Adversarial Robustness of Large Vision-Language Models
https://github.com/yuyuwu5/ADR
공식 코드Annealing Self-Distillation Rectification Improves Adversarial Training
https://github.com/zdhnarsil/margin-boosting
공식 코드https://github.com/zero-one-loss/mlp01
공식 코드https://github.com/zfancy/iad
공식 코드https://github.com/zhangcen456/ib
공식 코드Improving the Adversarial Robustness of NLP Models by Information Bottleneck
https://github.com/zhaoshiji123/absld
공식 코드Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
https://github.com/zhaoshiji123/aw-net
공식 코드Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters
https://github.com/zhaoshiji123/mtard-extension
공식 코드Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
https://github.com/zhichao-lu/robust-residual-network
공식 코드Revisiting Residual Networks for Adversarial Robustness: An Architectural Perspective
https://github.com/zhongjian-zhang/llm4rgnn
공식 코드Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?
https://github.com/zhouxiaowei1120/ladder
공식 코드https://github.com/zhouzhengqd/beard
공식 코드BEARD: Benchmarking the Adversarial Robustness for Dataset Distillation
https://github.com/zhyblue424/tga-zsr
공식 코드Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
https://github.com/zibojia/rslad
공식 코드Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better
https://github.com/ziquanliu/ICML2024-AT-UR
공식 코드The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
https://github.com/ziquanliu/cvpr2023-twins
공식 코드https://github.com/zixu1986/Doubly_Stochastic_Gradients
공식 코드Fast and Scalable Adversarial Training of Kernel SVM via Doubly Stochastic Gradients
https://github.com/zjfheart/noilin
공식 코드NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels
https://github.com/zjfheart/zjfheart.github.io
공식 코드CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
https://github.com/zjlab-ammi/lsd
공식 코드Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models
https://github.com/zknus/neurips-2023-hang-robustness
공식 코드Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
https://github.com/zl-helios/trajpac
공식 코드TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
https://github.com/zzj403/BEV_Robust
공식 코드https://github.com/zzzhangboya/scoreopt
공식 코드Enhancing Adversarial Robustness via Score-Based Optimization
https://gitlab.com/Bitterwolf/GOOD
공식 코드Certifiably Adversarially Robust Detection of Out-of-Distribution Data
https://gitlab.com/awadailab/faithful-contrastive-explanations
공식 코드https://worksheets.codalab.org/worksheets/0x9df253b24dac4a2b930108be9c6e5496
공식 코드https://github.com/2023-MindSpore-4/Code14/tree/main/SPADE
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
https://github.com/2023-MindSpore-4/Code16/tree/main/guitao/robust_ticket-main-main
https://github.com/AI-secure/Transferability-Reduced-Smooth-Ensemble
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/Abhishek2271/TransferabilityAnalysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.