Papers Backdoor Attack
“Backdoor Attack” 태그가 달린 논문 523편 · 필터 해제
VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation
Graphical User Interface (GUI) agents powered by Large Vision-Language Models (LVLMs) have emerged as a revolutionary approach to automating human-machine interactions, capable of autonomously operating personal devices …
Backdoor AttackVisual GroundingBeyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning
Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor attacks, which implant hidden triggers t…
Backdoor AttackDeep Reinforcement LearningCUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks
Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated…
Backdoor Attackbackdoor defenseScreen Hijack: Visual Poisoning of VLM Agents in Mobile Environments
With the growing integration of vision-language models (VLMs), mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated …
Backdoor AttackME: Trigger Element Combination Backdoor Attack on Copyright Infringement
The capability of generative diffusion models (DMs) like Stable Diffusion (SD) in replicating training data could be taken advantage of by attackers to launch the Copyright Infringement Attack, with duplicated poisoned i…
Backdoor AttackSingle-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems
Graph recommendation systems have been widely studied due to their ability to effectively capture the complex interactions between users and items. However, these systems also exhibit certain vulnerabilities when faced w…
Backdoor AttackRecommendation SystemsSPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models
Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptibl…
Backdoor AttackKeyword SpottingLanguage ModelingLanguage Modelling+2Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely …
Backdoor AttackData PoisoningInvisible Backdoor Triggers in Image Editing Model via Deep Watermarking
Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can…
Backdoor AttackImage GenerationHeterogeneous Graph Backdoor Attack
Heterogeneous Graph Neural Networks (HGNNs) excel in modeling complex, multi-typed relationships across diverse domains, yet their vulnerability to backdoor attacks remains unexplored. To address this gap, we conduct the…
Backdoor Attackbackdoor defensePoison in the Well: Feature Embedding Disruption in Backdoor Attacks
Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks…
Backdoor AttackBadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
Vision-Language-Action (VLA) models have advanced robotic control by enabling end-to-end decision-making directly from multimodal inputs. However, their tightly coupled architectures expose novel security vulnerabilities…
Backdoor AttackVision-Language-ActionBadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerability to backdoor attacks remains unexplored…
Autonomous DrivingBackdoor AttackDepth CompletionDepth Estimation+3Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet daily, possibly containing backdoors, and …
Backdoor AttackData PoisoningDeep Reinforcement Learningreinforcement-learning+2FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide inflexible attack control, or ignore emerg…
Autonomous DrivingBackdoor AttackTraffic Sign RecognitionDefending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning
Federated learning (FL) enhances privacy and reduces communication cost for resource-constrained edge clients by supporting distributed model training at the edge. However, the heterogeneous nature of such devices produc…
Backdoor AttackFederated LearningMixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-atta…
Backdoor AttackNatural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against…
Autonomous DrivingBackdoor AttackLanguage ModelingLanguage Modelling+3BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hij…
Backdoor AttackProtocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF Fingerprinting
While supervised deep neural networks (DNNs) have proven effective for device authentication via radio frequency (RF) fingerprinting, they are hindered by domain shift issues and the scarcity of labeled data. The success…
Backdoor Attack