Papers with Code 아카이브
Adversarial Attack Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
The detection of adversarial attacks.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/KaosEngineer/PriorNetworks
공식 코드Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
https://github.com/Shawn-Shan/trapdoor
공식 코드Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks
https://github.com/Sjtubrian/SAMMD
공식 코드Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
https://github.com/adverml/multilid
공식 코드Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
https://github.com/adverml/spectraldef_framework
공식 코드Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
https://github.com/c0510gy/AFLS-AED
공식 코드A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection
https://github.com/danushv07/n2gem
공식 코드Detecting Adversarial Examples in Batches -- a geometrical approach
https://github.com/joellliu/segmentandcomplete
공식 코드https://github.com/machanic/MetaAdvDet
공식 코드MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
https://github.com/qiulingxu/FeatureSpaceAttack
공식 코드https://github.com/rainavyas/naacl-2022-residue-detector
공식 코드https://github.com/ryuryukke/OUTFOX
공식 코드https://github.com/sohaib730/argos-adversarial_detection
공식 코드https://github.com/adverML/SAMMD
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
https://github.com/dwightnw/graph_based_methods_for_adversarial_attack
Graph-based methods coupled with specific distributional distances for adversarial attack detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.