Papers Data Poisoning
“Data Poisoning” 태그가 달린 논문 492편 · 필터 해제
A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning
Federated learning (FL) enables collaborative model training across decentralized clients while preserving data privacy. However, its open-participation nature exposes it to data-poisoning attacks, in which malicious act…
Data PoisoningFederated LearningSelf-Adaptive and Robust Federated Spectrum Sensing without Benign Majority for Cellular Networks
Advancements in wireless and mobile technologies, including 5G advanced and the envisioned 6G, are driving exponential growth in wireless devices. However, this rapid expansion exacerbates spectrum scarcity, posing a cri…
Data PoisoningFederated LearningMulti-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing…
Data PoisoningAddressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
Our research addresses the overlooked security concerns related to data poisoning in continual learning (CL). Data poisoning - the intentional manipulation of training data to affect the predictions of machine learning m…
Continual LearningData PoisoningExemplar-FreeTuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training
Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, its reliance on large volumes of labeled data raises privacy and security concerns suc…
Data PoisoningGeneralization BoundsGeneralization under Byzantine & Poisoning Attacks: Tight Stability Bounds in Robust Distributed Learning
Robust distributed learning algorithms aim to maintain good performance in distributed and federated settings, even in the presence of misbehaving workers. Two primary threat models have been studied: Byzantine attacks, …
Data PoisoningWinter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace…
Data PoisoningMemorizationData Shifts Hurt CoT: A Theoretical Study
Chain of Thought (CoT) has been applied to various large language models (LLMs) and proven to be effective in improving the quality of outputs. In recent studies, transformers are proven to have absolute upper bounds in …
Data PoisoningTED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics (TED) has recently emerged as …
backdoor defenseData PoisoningDevil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
Graph neural networks (GNNs) have achieved significant success in graph representation learning and have been applied to various domains. However, many real-world graphs contain sensitive personal information, such as us…
Data PoisoningGraph LearningGraph Representation LearningNode Classification+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 PoisoningSecuring Traffic Sign Recognition Systems in Autonomous Vehicles
Deep Neural Networks (DNNs) are widely used for traffic sign recognition because they can automatically extract high-level features from images. These DNNs are trained on large-scale datasets obtained from unknown source…
Autonomous VehiclesData AugmentationData PoisoningTraffic Sign RecognitionVLMs Can Aggregate Scattered Training Patches
One way to mitigate risks in vision-language models (VLMs) is to remove dangerous samples in their training data. However, such data moderation can be easily bypassed when harmful images are split into small, benign-look…
Data PoisoningCascading Adversarial Bias from Injection to Distillation in Language Models
Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation…
Bias DetectionCode GenerationData PoisoningAdversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems
Retrieval-Augmented Generation (RAG) systems, which integrate Large Language Models (LLMs) with external knowledge sources, are vulnerable to a range of adversarial attack vectors. This paper examines the importance of R…
Adversarial AttackData PoisoningManagementRAG+2Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats
In connected and autonomous vehicles, machine learning for safety message classification has become critical for detecting malicious or anomalous behavior. However, conventional approaches that rely on centralized data c…
Anomaly DetectionAutonomous VehiclesData PoisoningFederated LearningAre Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains
Time Series Foundation Models (TSFMs), which are pretrained on large-scale, cross-domain data and capable of zero-shot forecasting in new scenarios without further training, are increasingly adopted in real-world applica…
Adversarial RobustnessData PoisoningTime SeriesSecurity Concerns for Large Language Models: A Survey
Large Language Models (LLMs) such as GPT-4 and its recent iterations, Google's Gemini, Anthropic's Claude 3 models, and xAI's Grok have caused a revolution in natural language processing, but their capabilities also intr…
Data PoisoningSurveyBackdoors 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+2BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
With the widespread application of super-resolution (SR) in various fields, researchers have begun to investigate its security. Previous studies have demonstrated that SR models can also be subjected to backdoor attacks …
Data PoisoningImage Super-ResolutionSuper-Resolution