https://github.com/tuananhbui89/Crossing-Collaborative-Ensemble
공식 코드Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness
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/tzee/ekdaa-release
공식 코드https://github.com/ubc-systopia/adaptive-randomized-smoothing
공식 코드Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
https://github.com/ucla-seal/sibyl
공식 코드https://github.com/uclanlp/nlp-interpretation-faithfulness
공식 코드On the Sensitivity and Stability of Model Interpretations in NLP
https://github.com/ucr-optml/FedNest
공식 코드FedNest: Federated Bilevel, Minimax, and Compositional Optimization
https://github.com/ucsb-nlp-chang/textgrad
공식 코드TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
https://github.com/ucsc-vlaa/vllm-safety-benchmark
공식 코드How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
https://github.com/uds-lsv/evaluating-logit-pairing-methods
공식 코드https://github.com/uiuc-focal-lab/ramp
공식 코드RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
https://github.com/usail-hkust/rdat
공식 코드Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training
https://github.com/usc-sail/gard-adversarial-speaker-id
공식 코드Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems
https://github.com/ustunb/reach-ml
공식 코드Prediction without Preclusion: Recourse Verification with Reachable Sets
https://github.com/val-iisc/BPFC
공식 코드Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes
https://github.com/val-iisc/flss
공식 코드Boosting Adversarial Robustness using Feature Level Stochastic Smoothing
https://github.com/val-iisc/nu-certified-robustness
공식 코드Certified Adversarial Robustness Within Multiple Perturbation Bounds
https://github.com/val-iisc/oaat
공식 코드https://github.com/vcl-iisc/data-free-black-box-defense
공식 코드Data-free Defense of Black Box Models Against Adversarial Attacks
https://github.com/vcl-iisc/data-free-defense-at-test-time
공식 코드https://github.com/vcl-iisc/improved-data-free-test-time-adversarial-defense
공식 코드https://github.com/viethoang1512/glot
공식 코드https://github.com/visionflow/srouda_main
공식 코드SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation
https://github.com/vita-group/random_pruning
공식 코드https://github.com/vlgiitr/llm-math
공식 코드Give me a hint: Can LLMs take a hint to solve math problems?
https://github.com/vtddggg/CAA
공식 코드https://github.com/vvoracek/rs_conf_seq
공식 코드Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
https://github.com/wagner-group/demystify-random-transform
공식 코드Demystifying the Adversarial Robustness of Random Transformation Defenses
https://github.com/wagner-group/geoadex
공식 코드Adversarial Examples for $k$-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams
https://github.com/walkerning/aw_nas
공식 코드https://github.com/wangjksjtu/minmax-adv
공식 코드Adversarial Attack Generation Empowered by Min-Max Optimization
https://github.com/wangren09/MetaAdv
공식 코드On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
https://github.com/wangren09/RAILS
공식 코드https://github.com/wangren09/mcgr
공식 코드https://github.com/weizeming/sam_at
공식 코드Sharpness-Aware Minimization Alone can Improve Adversarial Robustness
https://github.com/weizeming/z3_for_verification_of_fnn_global_robustness
공식 코드Using Z3 for Formal Modeling and Verification of FNN Global Robustness
https://github.com/whiteteadragon/practical_svd_conv
공식 코드Towards Practical Control of Singular Values of Convolutional Layers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.