Papers with Code 아카이브
Data Poisoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Data Poisoning is an adversarial attack that tries to manipulate the training dataset in order to control the prediction behavior of a trained model such that the model will label malicious examples into a desired classes (e.g., labeling spam e-mails as safe).
Source: Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
Fed-Credit: Robust Federated Learning with Credibility Management
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
On the Relevance of Byzantine Robust Optimization Against Data Poisoning
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Code
Don't Forget What I did?: Assessing Client Contributions in Federated Learning
Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks
Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
Learning to Poison Large Language Models for Downstream Manipulation
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
Purifying Large Language Models by Ensembling a Small Language Model
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
SusFL: Energy-Aware Federated Learning-based Monitoring for Sustainable Smart Farms
Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
The Effect of Data Poisoning on Counterfactual Explanations
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Game-Theoretic Unlearnable Example Generator
Security and Privacy Challenges of Large Language Models: A Survey
Federated Learning with Dual Attention for Robust Modulation Classification under Attacks
A GAN-based data poisoning framework against anomaly detection in vertical federated learning
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline
Data-Dependent Stability Analysis of Adversarial Training
SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.