https://github.com/rainavyas/nlp_attackability
공식 코드Sample Attackability in Natural Language Adversarial Attacks
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/rainavyas/prepend_acoustic_attack
공식 코드Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models
https://github.com/rajabia/mdtd
공식 코드MDTD: A Multi Domain Trojan Detector for Deep Neural Networks
https://github.com/ralphc1212/amortized-approximation-of-induced-distribution
공식 코드Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
https://github.com/raphaelolivier/sparsity
공식 코드How many perturbations break this model? Evaluating robustness beyond adversarial accuracy
https://github.com/razla/foiling-explanations-in-deep-neural-networks
공식 코드https://github.com/realcrane/BASAR-Black-box-Attack-on-Skeletal-Action-Recognition
공식 코드https://github.com/realcrane/SMART
공식 코드Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
https://github.com/reedscot/icml2016
공식 코드https://github.com/reek129/QuantumAI_MultiClass_Sign_Recognition
공식 코드https://github.com/renmin1991/perturbation-inactivate
공식 코드Perturbation Inactivation Based Adversarial Defense for Face Recognition
https://github.com/retsuh-bqw/fmp
공식 코드https://github.com/reviewadvexample/revew_adv_defense
공식 코드A Review of Adversarial Attack and Defense for Classification Methods
https://github.com/rfww/spy-watermark
공식 코드Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
https://github.com/rgerum/spectral-representations
공식 코드Different Spectral Representations in Optimized Artificial Neural Networks and Brains
https://github.com/rinnesz/clga
공식 코드Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation
https://github.com/riolys/disdiff
공식 코드Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization
https://github.com/rjduan/advdrop
공식 코드https://github.com/robin-wzq/daa
공식 코드Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
https://github.com/robin-wzq/iba
공식 코드Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model
https://github.com/robin-wzq/t2ishield
공식 코드T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
https://github.com/rohban-lab/trodo
공식 코드https://github.com/roywang021/UMK
공식 코드White-box Multimodal Jailbreaks Against Large Vision-Language Models
https://github.com/ru-system-software-and-security/none
공식 코드Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
https://github.com/ru-system-software-and-security/unicorn
공식 코드https://github.com/ruocwang/dpo-diffusion
공식 코드https://github.com/ruoxi-jia-group/narcissus-backdoor-attack
공식 코드Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
https://github.com/ruyue0001/backdoor_dpr
공식 코드Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval Systems
https://github.com/ryderling/adversarial-attacks-and-defenses-for-windows-pe-malware-detection
공식 코드Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art
https://github.com/ryime/pdsg-sda
공식 코드https://github.com/ryliu68/CDMA
공식 코드Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models
https://github.com/ryuryukke/OUTFOX
공식 코드https://github.com/s4nyam/gradcam-yolo
공식 코드Adversarial Attack On Yolov5 For Traffic And Road Sign Detection
https://github.com/safe-graph/graph-adversarial-learning-literature
공식 코드https://github.com/sail-sg/anydoor
공식 코드Test-Time Backdoor Attacks on Multimodal Large Language Models
https://github.com/salijona/c-advdgm
공식 코드Deep generative models as an adversarial attack strategy for tabular machine learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.