Papers with Code 아카이브
Backdoor Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression
iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
A general approach to enhance the survivability of backdoor attacks by decision path coupling
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval Systems
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
Backdoor Attack against One-Class Sequential Anomaly Detection Models
Test-Time Backdoor Attacks on Multimodal Large Language Models
OrderBkd: Textual backdoor attack through repositioning
DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models
The last Dance : Robust backdoor attack via diffusion models and bayesian approach
Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Inferring Properties of Graph Neural Networks
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks
Object-oriented backdoor attack against image captioning
Effective backdoor attack on graph neural networks in link prediction tasks
Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers
Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?
Does Few-shot Learning Suffer from Backdoor Attacks?
SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
A clean-label graph backdoor attack method in node classification task
Punctuation Matters! Stealthy Backdoor Attack for Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.