Papers with Code 아카이브

Adversarial Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/craymichael/unfooling

공식 코드

Unfooling Perturbation-Based Post Hoc Explainers

https://github.com/cristinalan/flowmur

공식 코드

FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge

https://github.com/csjunjun/difattack

공식 코드

DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain

https://github.com/cuge1995/Mesh-Attack

공식 코드

3D Adversarial Attacks Beyond Point Cloud

https://github.com/cv-stuttgart/pcfa

공식 코드

A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow

https://github.com/cxmscb/ATDA

공식 코드

Improving the Generalization of Adversarial Training with Domain Adaptation

https://github.com/cyhuang-tw/attack-vc

공식 코드

Defending Your Voice: Adversarial Attack on Voice Conversion

https://github.com/cyr19/menli

공식 코드

MENLI: Robust Evaluation Metrics from Natural Language Inference

https://github.com/cywinski/saeuron

공식 코드

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

https://github.com/daizy97/saliencyattack

공식 코드

Saliency Attack: Towards Imperceptible Black-box Adversarial Attack

https://github.com/damianliumin/non-adversarial_backdoor

공식 코드

Beating Backdoor Attack at Its Own Game

https://github.com/daniel-xsy/bev-attack

공식 코드

On the Adversarial Robustness of Camera-based 3D Object Detection

https://github.com/danushv07/n2gem

공식 코드

Detecting Adversarial Examples in Batches -- a geometrical approach

https://github.com/data-iitd/advtpp

공식 코드

Differentiable Adversarial Attacks for Marked Temporal Point Processes

https://github.com/datar001/awesome-ad-on-t2idm

공식 코드

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey

https://github.com/datar001/revealing-vulnerabilities-in-stable-diffusion-via-targeted-attacks

공식 코드

Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks

https://github.com/datasec-lab/codebreaker

공식 코드

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

https://github.com/david-li0406/read

공식 코드

READ: Improving Relation Extraction from an ADversarial Perspective

https://github.com/davide-coccomini/adversarial-magnification-to-deceive-deepfake-detection-through-super-resolution

공식 코드

Adversarial Magnification to Deceive Deepfake Detection through Super Resolution

https://github.com/davidherel/semantics-preserving-encoder

공식 코드

Preserving Semantics in Textual Adversarial Attacks

https://github.com/dbash/pix2pix_cyclegan_guess_noise

공식 코드

Adversarial Self-Defense for Cycle-Consistent GANs

https://github.com/deel-ai-papers/lip-rcp

공식 코드

Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks

https://github.com/demelin/detecting_wsd_biases_for_nmt

공식 코드

Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks

https://github.com/dependable-cps/adversarial-MTSR

공식 코드

Adversarial Examples in Deep Learning for Multivariate Time Series Regression

https://github.com/derryhub/fairmot-attack

공식 코드

Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers

https://github.com/dig-beihang/x-adv

공식 코드

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

https://github.com/discovershu/orat

공식 코드

Outlier Robust Adversarial Training

https://github.com/django-jiang/badchain

공식 코드

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

https://github.com/dongyp13/Non-Targeted-Adversarial-Attacks

공식 코드

Boosting Adversarial Attacks with Momentum

https://github.com/dongyp13/Targeted-Adversarial-Attack

공식 코드

Boosting Adversarial Attacks with Momentum

https://github.com/dravyanshsharma/adversarial-contrastive

공식 코드

An Analysis of Robustness of Non-Lipschitz Networks

https://github.com/dydjw9/MetaAttack_ICLR2020

공식 코드

Query-efficient Meta Attack to Deep Neural Networks

https://github.com/eclipse-bot/sa-attack

공식 코드

SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory prediction

https://github.com/ecrows/cgtext-detection-adv

공식 코드

Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers

https://github.com/edosedgar/mtcnnattack

공식 코드

Real-world adversarial attack on MTCNN face detection system

https://github.com/ehsannowroozi/rdfs_su

공식 코드

Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.