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.
TrojanRobot: Physical-World Backdoor Attacks Against VLM-based Robotic Manipulation
Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
Act in Collusion: A Persistent Distributed Multi-Target Backdoor in Federated Learning
Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras
Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion
Securing Federated Learning against Backdoor Threats with Foundation Model Integration
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations
Backdoor Attack on Vertical Federated Graph Neural Network Learning
CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
BadHMP: Backdoor Attack against Human Motion Prediction
Psychometrics for Hypnopaedia-Aware Machinery via Chaotic Projection of Artificial Mental Imagery
TrojVLM: Backdoor Attack Against Vision Language Models
Weak-to-Strong Backdoor Attack for Large Language Models
Claim-Guided Textual Backdoor Attack for Practical Applications
Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks
SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
Data-centric NLP Backdoor Defense from the Lens of Memorization
PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning
A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor
NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise
EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models
SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning
MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer
Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
MEGen: Generative Backdoor in Large Language Models via Model Editing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.