https://github.com/jeffreyzpan/adversarial-playground
공식 코드On Intrinsic Dataset Properties for Adversarial Machine Learning
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/jeongjin0/invisible-backdoor-object-detection
공식 코드https://github.com/jeromerony/alma_prox_segmentation
공식 코드Proximal Splitting Adversarial Attacks for Semantic Segmentation
https://github.com/jeromerony/augmented_lagrangian_adversarial_attacks
공식 코드https://github.com/jhcknzzm/federated-learning-backdoor
공식 코드https://github.com/jhl-hust/svre
공식 코드Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
https://github.com/jhl-hust/texthacker
공식 코드TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack
https://github.com/jhl-hust/trasw
공식 코드Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
https://github.com/jiah-li/magic
공식 코드Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models
https://github.com/jiahaowugit/bgc
공식 코드https://github.com/jiawangbai/TA-LBF
공식 코드Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
https://github.com/jiawangbai/versatile-weight-attack
공식 코드https://github.com/jiaxiaojunqaq/fgsm-pgi
공식 코드Prior-Guided Adversarial Initialization for Fast Adversarial Training
https://github.com/jiaxiaojunqaq/foa-attack
공식 코드Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
https://github.com/jiaxiaojunqaq/sa-aet
공식 코드Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
https://github.com/jiazhaoli/attdef
공식 코드Defending against Insertion-based Textual Backdoor Attacks via Attribution
https://github.com/jimmy-academia/lasgsa
공식 코드https://github.com/jind11/TextFooler
공식 코드https://github.com/jinghuichen/Focused-Flip-Federated-Backdoor-Attack
공식 코드On the Vulnerability of Backdoor Defenses for Federated Learning
https://github.com/jinlong17/advgps
공식 코드https://github.com/jinxhy/smartappattack
공식 코드Smart App Attack: Hacking Deep Learning Models in Android Apps
https://github.com/jinxhy/tflexattack
공식 코드https://github.com/jinzhuoran/rwku
공식 코드RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
https://github.com/jj-vice/bagm
공식 코드BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models
https://github.com/jjhuangcs/advinn
공식 코드Imperceptible Adversarial Attack via Invertible Neural Networks
https://github.com/jjy1994/BadEncoder
공식 코드BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
https://github.com/joellliu/segmentandcomplete
공식 코드https://github.com/john-niu-07/pud
공식 코드Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
https://github.com/jonasrauber/linear-region-attack
공식 코드https://github.com/jonrusert/binaryselect
공식 코드BinarySelect to Improve Accessibility of Black-Box Attack Research
https://github.com/josephcao0327/stylefool
공식 코드StyleFool: Fooling Video Classification Systems via Style Transfer
https://github.com/joshuajss/RTAA
공식 코드https://github.com/jpark04-qub/sqba
공식 코드https://github.com/jrohsc/backdororing_bias
공식 코드https://github.com/jubueche/spaa
공식 코드Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based Vision
https://github.com/judydnguyen/pbp-backdoor-purification-official
공식 코드PBP: Post-training Backdoor Purification for Malware Classifiers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.