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/cburgerolemiss/xaifooler
공식 코드https://github.com/cdluminate/advorder
공식 코드https://github.com/cdluminate/advrank
공식 코드https://github.com/cdluminate/robrank
공식 코드https://github.com/cecilialeiqi/adversarial_text
공식 코드Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
https://github.com/cfinlay/tulip
공식 코드Scaleable input gradient regularization for adversarial robustness
https://github.com/cgcl-codes/attack_ptmc
공식 코드An Extensive Study on Adversarial Attack against Pre-trained Models of Code
https://github.com/cgcl-codes/badhash
공식 코드BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
https://github.com/changzhang777/ancra
공식 코드Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
https://github.com/chaowang1016/asd
공식 코드Spatial-Frequency Discriminability for Revealing Adversarial Perturbations
https://github.com/charles-ydd/trojanrag
공식 코드TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
https://github.com/chasesecurity/spamdam
공식 코드SpamDam: Towards Privacy-Preserving and Adversary-Resistant SMS Spam Detection
https://github.com/chauhanjatin10/bertops
공식 코드BERTops: Studying BERT Representations under a Topological Lens
https://github.com/chelungungun/Transferability_MLATTACK
공식 코드Attack Transferability Characterization for Adversarially Robust Multi-label Classification
https://github.com/chengxuduan/advhmp
공식 코드Physics-constrained Attack against Convolution-based Human Motion Prediction
https://github.com/chengyinhu/advls
공식 코드Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs
https://github.com/chenhongge/RobustTrees
공식 코드https://github.com/chenwu98/agent-attack
공식 코드https://github.com/chichidd/backdoordynamicdnn
공식 코드Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
https://github.com/chnanchan/psp-uap
공식 코드Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
https://github.com/chong-z/tree-ensemble-attack
공식 코드https://github.com/chs20/robustvlm
공식 코드On the Adversarial Robustness of Multi-Modal Foundation Models
https://github.com/chunfengc/ASNet
공식 코드Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
https://github.com/cihangxie/DI-2-FGSM
공식 코드Improving Transferability of Adversarial Examples with Input Diversity
https://github.com/cinderyl/lidattack
공식 코드LiDAttack: Robust Black-box Attack on LiDAR-based Object Detection
https://github.com/cinofix/poisoning-clustering
공식 코드https://github.com/ckgconstruction/bdcp
공식 코드Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification
https://github.com/ckvermaai/snli-attack-analysis
공식 코드Unpacking the Resilience of SNLI Contradiction Examples to Attacks
https://github.com/clawero-o/asma
공식 코드Imperceptible Face Forgery Attack via Adversarial Semantic Mask
https://github.com/cmhcbb/attackbox
공식 코드https://github.com/cmu-enyac/Renofeation
공식 코드Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness
https://github.com/code-Assasin/A_Little_fog_for_a_Large_Turn
공식 코드https://github.com/collinzrj/adversarial_decoding
공식 코드Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
https://github.com/confirm-solutions/dreamy
공식 코드https://github.com/cookielee77/CLARE
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.