Papers with Code 아카이브
Adversarial Purification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
A class of adversarial defense methods that remove adversarial perturbations using a generative model.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
Adversarial Purification of Information Masking
Diffusion models meet image counter-forensics
Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models
Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
Diffusion-Based Adversarial Purification for Speaker Verification
Language Guided Adversarial Purification
Advancing Adversarial Robustness Through Adversarial Logit Update
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing
Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models
Rapid Plug-in Defenders
Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial Robustness
Robust Evaluation of Diffusion-Based Adversarial Purification
Defending against Adversarial Audio via Diffusion Model
Adversarial Purification with the Manifold Hypothesis
Towards Adversarial Purification using Denoising AutoEncoders
Guided Diffusion Model for Adversarial Purification from Random Noise
Guided Diffusion Model for Adversarial Purification
Diffusion Models for Adversarial Purification
Text Adversarial Purification as Defense against Adversarial Attacks
Adversarial Purification through Representation Disentanglement
Adversarial purification with Score-based generative models
Online Adversarial Purification based on Self-Supervision
Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.