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/TaoShuchang/AdvImmune

공식 코드

Adversarial Immunization for Certifiable Robustness on Graphs

https://github.com/Tencent/TFace/tree/Adv-Attack-Defense/security/tasks/Adv-Attack-Defense/Sibling-Attack

공식 코드

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition

https://github.com/TenneyHu/CrossLingualAttack

공식 코드

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers

https://github.com/TheaperDeng/GNN-Attack-InfMax

공식 코드

Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem

https://github.com/Tianyaz97/rf_backdoor

공식 코드

Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF Fingerprinting

https://github.com/TinfoilHat0/Defending-Against-Backdoors-with-Robust-Learning-Rate

공식 코드

Defending against Backdoors in Federated Learning with Robust Learning Rate

https://github.com/Top-Ranger/text_adversarial_attack

공식 코드

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples

https://github.com/TransEmbedBA/TREMBA

공식 코드

Black-Box Adversarial Attack with Transferable Model-based Embedding

https://github.com/TrustAI/DeepGame

공식 코드

A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees

https://github.com/TrustAI/GUAP

공식 코드

Generalizing Universal Adversarial Attacks Beyond Additive Perturbations

https://github.com/TrustworthyDL/LeBA

공식 코드

Learning Black-Box Attackers with Transferable Priors and Query Feedback

https://github.com/UKPLab/naacl2019-like-humans-visual-attacks

공식 코드

Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems

https://github.com/UMBCvision/Contextual-Adversarial-Patches

공식 코드

Role of Spatial Context in Adversarial Robustness for Object Detection

https://github.com/UMBCvision/Hidden-Trigger-Backdoor-Attacks

공식 코드

Hidden Trigger Backdoor Attacks

https://github.com/UMBCvision/SSL-Backdoor

공식 코드

Backdoor Attacks on Self-Supervised Learning

https://github.com/UTibetNLP/TSTricker

공식 코드

Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model

https://github.com/VISION-SJTU/IoUattack

공식 코드

IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking

https://github.com/VITA-Group/SparseADV_Homotopy

공식 코드

Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm

https://github.com/VeriDeep/DLV

공식 코드

Safety Verification of Deep Neural Networks

https://github.com/Vill-Lab/2023-TIFS-DTIBA

공식 코드

Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification

https://github.com/VinAIResearch/Warping-based_Backdoor_Attack-release

공식 코드

WaNet -- Imperceptible Warping-based Backdoor Attack

https://github.com/VinAIResearch/input-aware-backdoor-attack-release

공식 코드

Input-Aware Dynamic Backdoor Attack

https://github.com/WJJLL/SVD-SSA

공식 코드

Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature

https://github.com/WinnieHAN/structure_adv

공식 코드

Adversarial Attack and Defense of Structured Prediction Models

https://github.com/XMUDM/AUSH

공식 코드

Attacking Recommender Systems with Augmented User Profiles

https://github.com/YiZeng623/FenceBox

공식 코드

FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation Techniques

https://github.com/YuanGongND/realtime-adversarial-attack

공식 코드

Real-Time Adversarial Attacks

https://github.com/Yuxin-Wen/GeoA3

공식 코드

Geometry-Aware Generation of Adversarial Point Clouds

https://github.com/ZhongliangGuo/LAACA

공식 코드

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

https://github.com/ZiangYan/subspace-attack.pytorch

공식 코드

Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks

https://github.com/aaaaaasuka/datafree_backdoor_attacks

공식 코드

Data Free Backdoor Attacks

https://github.com/aam-at/adversary_critic

공식 코드

Improved Network Robustness with Adversary Critic

https://github.com/aam-at/cpgd

공식 코드

PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack

https://github.com/adelsamir01/cyberllminstruct

공식 코드

CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data

https://github.com/advattack/bu-spo

공식 코드

Semantic-Preserving Adversarial Text Attacks

https://github.com/advboxes/AdvBox

공식 코드

Attacking and Defending Machine Learning Applications of Public Cloud

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