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/ydc123/Dark_Surrogate_Model

공식 코드

Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge

https://github.com/ydc123/mmp-attack

공식 코드

On the Multi-modal Vulnerability of Diffusion Models

https://github.com/yeshaokai/Calibrator-Domain-Adaptation

공식 코드

Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

https://github.com/yexind/dsne

공식 코드

Adversarial Attack via Dual-Stage Network Erosion

https://github.com/yibin-lei/plat

공식 코드

Phrase-level Textual Adversarial Attack with Label Preservation

https://github.com/yibo-miao/pbo-attack

공식 코드

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

https://github.com/yihuang2016/TAIG

공식 코드

Transferable Adversarial Attack based on Integrated Gradients

https://github.com/yinghuagao/siba

공식 코드

Backdoor Attack with Sparse and Invisible Trigger

https://github.com/ylhz/natural-color-fool

공식 코드

Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks

https://github.com/yonggangzhangustc/causaladv

공식 코드

CausalAdv: Adversarial Robustness through the Lens of Causality

https://github.com/yonghaoxu/uae-rs

공식 코드

Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark

https://github.com/yonxie/advfintweet

공식 코드

A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions

https://github.com/ypotdevin/randomized-defenses

공식 코드

An Empirical Investigation of Randomized Defenses against Adversarial Attacks

https://github.com/ysharma1126/EAD-Attack

공식 코드

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

https://github.com/ysharma1126/caad_18

공식 코드

CAAD 2018: Generating Transferable Adversarial Examples

https://github.com/yuchen-sunflower/tkmia

공식 코드

When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-$k$ Multi-Label Learning

https://github.com/yueeeeeeee/recsys-substitution-defense

공식 코드

Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders

https://github.com/yul091/dgslow

공식 코드

White-Box Multi-Objective Adversarial Attack on Dialogue Generation

https://github.com/yulongtzzz/Stealthy-Backdoors-as-Compression-Artifacts

공식 코드

Stealthy Backdoors as Compression Artifacts

https://github.com/yuweisunn/ADA

공식 코드

Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis

https://github.com/yuyang-long/ssa

공식 코드

Frequency Domain Model Augmentation for Adversarial Attack

https://github.com/yuyi-sd/baiqa

공식 코드

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger

https://github.com/zaixizhang/cbd

공식 코드

Backdoor Defense via Deconfounded Representation Learning

https://github.com/zaixizhang/graphbackdoor

공식 코드

Backdoor Attacks to Graph Neural Networks

https://github.com/zaynmi/seada-vqa

공식 코드

Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering

https://github.com/zblasingame/adjointdeis

공식 코드

AdjointDEIS: Efficient Gradients for Diffusion Models

https://github.com/zero-one-loss/wordcnn01

공식 코드

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble

https://github.com/zetangforward/csa-gec

공식 코드

Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting

https://github.com/zeyuanyin/LTH-Backdoor

공식 코드

Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis

https://github.com/zhaitongqing233/Backdoor-attack-against-speaker-verification

공식 코드

Backdoor Attack against Speaker Verification

https://github.com/zhang-henry/imperative

공식 코드

Towards Imperceptible Backdoor Attack in Self-supervised Learning

https://github.com/zhang-wy15/Attack_practical_asv

공식 코드

Attack on practical speaker verification system using universal adversarial perturbations

https://github.com/zhangr2021/clcts

공식 코드

Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation

https://github.com/zhangsn-19/pan

공식 코드

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

https://github.com/zhangyxrepo/disttack

공식 코드

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training

https://github.com/zhanliqxq/capaa

공식 코드

CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack

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