Image de couverture de livre

Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Verma, Sahil, Bhatt, Gantavya, Schwarzschild, Avi, Singhal, Soumye, Das, Arnav Mohanty, Shah, Chirag, Dickerson, John P, Chen, Pin-Yu, Bilmes, Jeff
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Deep Submodular Peripteral Networks
par: Bhatt, Gantavya, et autres
Publié: (2024)

COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation
par: Das, Arnav M., et autres
Publié: (2024)

How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
par: Bilmes, Jeff A., et autres
Publié: (2026)

How Many Images Does It Take? Estimating Imitation Thresholds in Text-to-Image Models
par: Verma, Sahil, et autres
Publié: (2024)

LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning
par: Zhang, Jifan, et autres
Publié: (2023)

Domain-Specific Self-Supervised Pre-training for Agricultural Disease Classification: A Hierarchical Vision Transformer Study
par: Sonavane, Arnav S.
Publié: (2026)

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
par: Bhatt, Gantavya, et autres
Publié: (2024)

Many-Objective Multi-Solution Transport
par: Li, Ziyue, et autres
Publié: (2024)

OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities
par: Verma, Sahil, et autres
Publié: (2025)

Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?
par: Han, TIngxu, et autres
Publié: (2024)

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
par: Han, Tingxu, et autres
Publié: (2024)

A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning
par: Gai, Keke, et autres
Publié: (2025)

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models
par: Zhao, Tianhang, et autres
Publié: (2025)

Benchmarking ChatGPT on Algorithmic Reasoning
par: McLeish, Sean, et autres
Publié: (2024)

Enabling High-Frequency Trading with Near-Instant, Trustless Cross-Chain Transactions via Pre-Signing Adaptor Signatures
par: Francolla, Ethan, et autres
Publié: (2025)

Backdoor Directions in Vision Transformers
par: Karayalcin, Sengim, et autres
Publié: (2026)

Evolved Sample Weights for Bias Mitigation: Effectiveness Depends on the Fairness Objective
par: Saini, Anil K., et autres
Publié: (2025)

Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
par: Das, Anindya Sundar, et autres
Publié: (2025)

iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics
par: Dammu, Preetam Prabhu Srikar, et autres
Publié: (2026)

Pure Event Semantics
par: Roger Schwarzschild
Publié: (2024)

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
par: Yang, Sheng, et autres
Publié: (2024)

Enhanced V2X Communication Using Game-Theory Based Adaptive MAC Protocols
par: Bhatt, Dhrumil, et autres
Publié: (2025)

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models
par: Liu, Yan, et autres
Publié: (2024)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
par: Chen, Hao, et autres
Publié: (2023)

Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
par: Levin, Roman, et autres
Publié: (2025)

Extrapolation by Association: Length Generalization Transfer in Transformers
par: Cai, Ziyang, et autres
Publié: (2025)

Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
par: Lee, Nayoung, et autres
Publié: (2025)

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
par: Williams, Joshua Nathaniel, et autres
Publié: (2024)

Forcing Diffuse Distributions out of Language Models
par: Zhang, Yiming, et autres
Publié: (2024)

From Prompt Engineering to Prompt Science With Human in the Loop
par: Shah, Chirag
Publié: (2024)

FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning
par: Wehbi, Osama, et autres
Publié: (2026)

Varesi, Gastón Ángel. Kirchnerismo y neodesarrollismo. Hegemonía, acumulación y relaciones de fuerzas en la Argentina. Buenos Aires: Luxemburg, 2021.
par: Julián Bilmes
Publié: (2023)

Battle of the Books: A Step-by-Step Approach
par: Bilmes, David
Publié: (2005)

Systolic Array-based Architecture for Low-Bit Integerized Vision Transformers
par: Lin, Ching-Yi, et autres
Publié: (2025)

UOR: Universal Backdoor Attacks on Pre-trained Language Models
par: Du, Wei, et autres
Publié: (2023)

Low-Bit Integerization of Vision Transformers using Operand Reordering for Efficient Hardware
par: Lin, Ching-Yi, et autres
Publié: (2025)

Enhancing Question Answering on Charts Through Effective Pre-training Tasks
par: Gupta, Ashim, et autres
Publié: (2024)

IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training
par: Liu, Che, et autres
Publié: (2023)

Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?
par: Chen, Xuezheng, et autres
Publié: (2025)

Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
par: Bansal, Hritik, et autres
Publié: (2024)