Cover Image

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Binyan, Yang, Fan, Dai, Xilin, Tang, Di, Zhang, Kehuan
Format:	Preprint
Published:	2025
Subjects:	Multimedia Cryptography and Security Machine Learning 68T07 I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
by: Xu, Binyan, et al.
Published: (2025)

Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
by: Xu, Binyan, et al.
Published: (2025)

Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution
by: Liu, Hongjun, et al.
Published: (2025)

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
by: Zhou, Xueyang, et al.
Published: (2025)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
by: Dang, Kieu, et al.
Published: (2025)

Explainable Attention-Based LSTM Framework for Early Detection of AI-Assisted Ransomware via File System Behavioral Analysis
by: Nayak, Prabhudarshi, et al.
Published: (2026)

"Abuse Risks are Often Inherent to Product Features": Exploring AI Vendors' Bug Bounty and Responsible Disclosure Policies
by: Piao, Yangheran, et al.
Published: (2025)

Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning
by: Niizumi, Daisuke, et al.
Published: (2026)

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
by: Hill, Brennen, et al.
Published: (2025)

A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems
by: Ismail, Nasim Abdirahman, et al.
Published: (2026)

BreakFun: Jailbreaking LLMs via Schema Exploitation
by: Oskooei, Amirkia Rafiei, et al.
Published: (2025)

Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization
by: Tu, Songjun, et al.
Published: (2025)

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks
by: Feng, Zhou, et al.
Published: (2025)

Robust DDoS-Attack Classification with 3D CNNs Against Adversarial Methods
by: Bragg, Landon, et al.
Published: (2025)

Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures
by: Mahi, Ishrak Hamim, et al.
Published: (2026)

The Age of Sensorial Zero Trust: Why We Can No Longer Trust Our Senses
by: Xavier, Fabio Correa
Published: (2025)

A V2X-based Privacy Preserving Federated Measuring and Learning System
by: Alekszejenkó, Levente, et al.
Published: (2024)

Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection
by: Chhetri, Rajeeb Thapa, et al.
Published: (2025)

The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
by: Brännvall, Rickard, et al.
Published: (2023)

Safety, Security, and Cognitive Risks in World Models
by: Parmar, Manoj
Published: (2026)

Machine Learning-Based Localization Accuracy of RFID Sensor Networks via RSSI Decision Trees and CAD Modeling for Defense Applications
by: Shull, Curtis Lee, et al.
Published: (2025)

Semantically Guided Adversarial Testing of Vision Models Using Language Models
by: Filus, Katarzyna, et al.
Published: (2025)

X-Factor: Quality Is a Dataset-Intrinsic Property
by: Couch, Josiah, et al.
Published: (2025)

DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
by: Lee, Chaeyoung, et al.
Published: (2026)

PACT: Reducing Alert Fatigue in Low-Prevalence SOC Streams with Triggered Active Learning
by: Ndichu, Samuel, et al.
Published: (2026)

Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
by: Ravindran, Santhosh Kumar
Published: (2026)

Illuminating the Black Box: Real-Time Monitoring of Backdoor Unlearning in CNNs via Explainable AI
by: Hoang, Tien Dat
Published: (2025)

FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification
by: Książek, Kamil, et al.
Published: (2025)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
by: Yamchote, Phaphontee, et al.
Published: (2025)

Hateful Meme Detection through Context-Sensitive Prompting and Fine-Grained Labeling
by: Ouyang, Rongxin, et al.
Published: (2024)

Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance
by: Yu, Hao, et al.
Published: (2026)

NeuronSpark: A Spiking Neural Network Language Model with Selective State Space Dynamics
by: Tang, Zhengzheng
Published: (2026)

Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning
by: Huff, Philip, et al.
Published: (2026)

Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy
by: Akgul, Hasan, et al.
Published: (2025)

RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series
by: Kumar, Indar, et al.
Published: (2026)

Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero
by: Maggiolo, Matteo, et al.
Published: (2025)

Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3
by: Nitarach, Natapong
Published: (2026)

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
by: Zhou, Xueyang, et al.
Published: (2025)

Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models
by: Jin, Cheng, et al.
Published: (2025)

Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems
by: Parris, William
Published: (2026)