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/amirhagai/on-adversarial-training-and-the-1-nearest-neighbor-classifier
공식 코드On adversarial training and the 1 Nearest Neighbor classifier
https://github.com/andreapatane/check-GPclass
공식 코드Adversarial Robustness Guarantees for Classification with Gaussian Processes
https://github.com/andyzoujm/pixmix
공식 코드PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
https://github.com/anguyen8/visual-correspondence-xai
공식 코드Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
https://github.com/aniloid2/confidence_elicitation_attacks
공식 코드Confidence Elicitation: A New Attack Vector for Large Language Models
https://github.com/anjilab/secure-private-ai
공식 코드Adversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentation
https://github.com/ankanbhunia/AdverseBiNet
공식 코드Improving Document Binarization via Adversarial Noise-Texture Augmentation
https://github.com/anminggu/kmixup-cifar10
공식 코드k-Mixup Regularization for Deep Learning via Optimal Transport
https://github.com/anneharrington/adversarially-robust-periphery
공식 코드Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks
https://github.com/anonymous-author-iccv2019/sanity_checks
공식 코드https://github.com/anonymous-koala-supporter/adversarial-deep-metric-learning
공식 코드https://github.com/aounon/center-smoothing
공식 코드Center Smoothing: Certified Robustness for Networks with Structured Outputs
https://github.com/arkadiyd/mo-pbt
공식 코드https://github.com/arobey1/mbrdl
공식 코드Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
https://github.com/arprl/arprl
공식 코드Learning Robust and Privacy-Preserving Representations via Information Theory
https://github.com/aryan-satpathy/backdoor
공식 코드Towards Adversarial Robustness And Backdoor Mitigation in SSL
https://github.com/asdfqwezxcf/advlatent
공식 코드Adversarial Machine Learning in Latent Representations of Neural Networks
https://github.com/autonomousvision/akorn
공식 코드https://github.com/babelscape/alert
공식 코드ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
https://github.com/bai-yt/adaptivesmoothing
공식 코드Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
https://github.com/bbartoldson/adversarial-robustness-limits
공식 코드Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
https://github.com/bbuing9/roast
공식 코드RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
https://github.com/bcv-uniandes/advseverity
공식 코드https://github.com/bcv-uniandes/rsr
공식 코드Generalized Real-World Super-Resolution through Adversarial Robustness
https://github.com/bdvllrs/generalization-vision
공식 코드https://github.com/bimalb58/logical-tsetlin-machine-robustness
공식 코드https://github.com/biqing-qi/exploring-adversarial-robustness-of-deep-state-space-models
공식 코드https://github.com/bjbbbb/enhancing-adversarial-robustness-with-conformal-prediction
공식 코드https://github.com/bkiani/Adversarial-robustness-guarantees-for-random-deep-neural-networks
공식 코드Adversarial Robustness Guarantees for Random Deep Neural Networks
https://github.com/blackswan-ai/circuit-breakers
공식 코드https://github.com/blackswan-ai/short-circuiting
공식 코드https://github.com/blaisedelattre/bridging_the_gap_rs
공식 코드https://github.com/bob-cheng/badpart
공식 코드BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
https://github.com/brianpulfer/robustness-tokens
공식 코드Robustness Tokens: Towards Adversarial Robustness of Transformers
https://github.com/buhuiok/taet-two-stage-adversarial-equalization-training-on-long-tailed-distributions
공식 코드TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.