Papers with Code 아카이브

Backdoor Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/najeebjebreel/dbalfa

공식 코드

Defending Against Backdoor Attacks by Layer-wise Feature Analysis

https://github.com/nanboy-ronan/backdoor-fedgan

공식 코드

Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis

https://github.com/narenmanoj/mnist-adv-training

공식 코드

Excess Capacity and Backdoor Poisoning

https://github.com/ndraeger/waba

공식 코드

Backdoor Attacks for Remote Sensing Data with Wavelet Transform

https://github.com/nguyenhongson1902/venomancer

공식 코드

Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning

https://github.com/nishadsinghi/cleanclip

공식 코드

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

https://github.com/optml-group/bibaddiff

공식 코드

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models

https://github.com/paoche11/gungnir

공식 코드

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models

https://github.com/papercgba/cgba

공식 코드

Claim-Guided Textual Backdoor Attack for Practical Applications

https://github.com/paperspapers/badprompt

공식 코드

BadPrompt: Backdoor Attacks on Continuous Prompts

https://github.com/phd-taoliu/fcba

공식 코드

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning

https://github.com/pku-ml/nlb

공식 코드

How to Craft Backdoors with Unlabeled Data Alone?

https://github.com/plasmashen/BackdoorPTM

공식 코드

Backdoor Pre-trained Models Can Transfer to All

https://github.com/qcznlp/uncertainty

공식 코드

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

https://github.com/qcznlp/uncertainty_attack

공식 코드

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

https://github.com/qsx830/mixbridge

공식 코드

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges

https://github.com/rajabia/mdtd

공식 코드

MDTD: A Multi Domain Trojan Detector for Deep Neural Networks

https://github.com/retsuh-bqw/fmp

공식 코드

Adversarial Feature Map Pruning for Backdoor

https://github.com/rfww/spy-watermark

공식 코드

Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack

https://github.com/robin-wzq/daa

공식 코드

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models

https://github.com/robin-wzq/iba

공식 코드

Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model

https://github.com/robin-wzq/t2ishield

공식 코드

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models

https://github.com/rohban-lab/trodo

공식 코드

Scanning Trojaned Models Using Out-of-Distribution Samples

https://github.com/ru-system-software-and-security/none

공식 코드

Training with More Confidence: Mitigating Injected and Natural Backdoors During Training

https://github.com/ru-system-software-and-security/unicorn

공식 코드

UNICORN: A Unified Backdoor Trigger Inversion Framework

https://github.com/ruoxi-jia-group/narcissus-backdoor-attack

공식 코드

Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information

https://github.com/ruyue0001/backdoor_dpr

공식 코드

Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval Systems

https://github.com/sail-sg/anydoor

공식 코드

Test-Time Backdoor Attacks on Multimodal Large Language Models

https://github.com/sclbd/backdoorbench

공식 코드

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

https://github.com/seaocn/link-backdoor

공식 코드

Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection

https://github.com/seaocn/motif-backdoor

공식 코드

Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs

https://github.com/secure-ai-systems-group/qu-anti-zation

공식 코드

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

https://github.com/serendipity618/ba-ocad

공식 코드

Backdoor Attack against One-Class Sequential Anomaly Detection Models

https://github.com/sf-zhai/badt2i

공식 코드

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning

https://github.com/shawkui/Proactive_Defensive_Backdoor

공식 코드

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor

https://github.com/shihe98/hcb

공식 코드

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense

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