Papers with Code 아카이브
Adversarial Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 3
- 보존된 평가 기록
- 9
An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.
Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Transferable Multiform Attack for Cross-Modal Person Re-Identification
3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving
VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models
Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF Infeasible
VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation
ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models
Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack
Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot Navigation
Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack
Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity
Constraint-Guided Prediction Refinement via Deterministic Diffusion Trajectories
On the existence of consistent adversarial attacks in high-dimensional linear classification
Second Order State Hallucinations for Adversarial Attack Mitigation in Formation Control of Multi-Agent Systems
Boosting Adversarial Transferability for Hyperspectral Image Classification Using 3D Structure-invariant Transformation and Intermediate Feature Distance
Unsourced Adversarial CAPTCHA: A Bi-Phase Adversarial CAPTCHA Framework
ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
A look at adversarial attacks on radio waveforms from discrete latent space
SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models
Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
Adversarial Text Generation with Dynamic Contextual Perturbation
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack
Learning Safety Constraints for Large Language Models
Heterogeneous Graph Backdoor Attack
3D Gaussian Splat Vulnerabilities
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.