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/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/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/zhenxianglance/cbd

공식 코드

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

https://github.com/zhou-cybersecurity-ai/synghost

공식 코드

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

https://github.com/zihao-ai/bot

공식 코드

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

https://github.com/zihao-ai/unthinking_vulnerability

공식 코드

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

https://github.com/zihao-ai/vdc

공식 코드

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models

https://github.com/zzwjames/dpgba

공식 코드

Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective

https://gitlab.idiap.ch/bob/bob.paper.neurips2024_model_pairing/

공식 코드

Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks

https://github.com/2023-MindSpore-4/Code12/tree/main/ganleilei/CleanLabelBackdoorAttackMindspore-master

Triggerless Backdoor Attack for NLP Tasks with Clean Labels

https://github.com/BililiCode/ARGD

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

https://github.com/DreamtaleCore/Refool

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

https://github.com/Guang000/Awesome-Dataset-Distillation

Backdoor Attacks Against Dataset Distillation

https://github.com/Jayfeather1024/Backdoor-Enhanced-Alignment

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

https://github.com/LiangSiyuan21/BadCLIP

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

https://github.com/Nathangitlab/Backdoor-Attacks-on-Crowd-Counting

Backdoor Attacks on Crowd Counting

https://github.com/TheLaoLab/UIBDiffusion

UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models

https://github.com/TrustAI/DeepConcolic

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers

https://github.com/ZJZAC/Poison-Ink

Poison Ink: Robust and Invisible Backdoor Attack

https://github.com/bboylyg/NAD

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

https://github.com/chamikara1986/BA-BAM

Resurrecting Trust in Facial Recognition: Mitigating Backdoor Attacks in Face Recognition to Prevent Potential Privacy Breaches

https://github.com/ethz-spylab/rlhf_trojan_competition

Universal Jailbreak Backdoors from Poisoned Human Feedback

https://github.com/giantseaweed/decree

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

https://github.com/igitugraz/outputcodematching

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

https://github.com/jeongjin0/detector-cleanse

BadDet: Backdoor Attacks on Object Detection

https://github.com/jinyuan-jia/badencoder

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

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

Backdoor Attacks on Self-Supervised Learning

https://github.com/jzhang538/corruptencoder

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning

https://github.com/lancopku/rap

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

https://github.com/linweiii/backdoordm

Invisible Backdoor Attacks on Diffusion Models

https://github.com/liu00222/StolenEncoder

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

https://github.com/locuslab/breaking-poisoned-classifier

Hidden Trigger Backdoor Attacks

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