Cover Image

Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Shuai, Gan, Leilei, Guo, Zhongliang, Wu, Xiaobao, Jia, Yanhao, Xiao, Luwei, Nguyen, Cong-Duy, Tuan, Luu Anh
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
by: Zhao, Shuai, et al.
Published: (2024)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
by: Zhao, Shuai, et al.
Published: (2025)

Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematurity
by: Zhao, Shuai, et al.
Published: (2025)

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
by: Zhao, Shuai, et al.
Published: (2024)

KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
by: Nguyen, Cong-Duy, et al.
Published: (2024)

CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base
by: Nguyen, Cong-Duy, et al.
Published: (2025)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
by: Zhao, Shuai, et al.
Published: (2024)

Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
by: Srey, Ponhvoan, et al.
Published: (2026)

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
by: Hu, Man, et al.
Published: (2025)

Vision-and-Language Pretraining
by: Nguyen, Thong, et al.
Published: (2022)

Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
by: Zhao, Shuai, et al.
Published: (2024)

Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
by: Feng, Yichao, et al.
Published: (2025)

Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions
by: Nguyen, Thong, et al.
Published: (2022)

Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation
by: Nguyen, Cong-Duy, et al.
Published: (2025)

A Survey on Neural Topic Models: Methods, Applications, and Challenges
by: Wu, Xiaobao, et al.
Published: (2024)

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
by: Le, Khoi, et al.
Published: (2026)

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
by: Zhao, Shuai, et al.
Published: (2023)

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding
by: Nguyen, Thong, et al.
Published: (2023)

Topic Modeling as Multi-Objective Contrastive Optimization
by: Nguyen, Thong, et al.
Published: (2024)

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention
by: Le, Dong, et al.
Published: (2026)

READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
by: Nguyen, Thong, et al.
Published: (2023)

Are LLMs Good Zero-Shot Fallacy Classifiers?
by: Pan, Fengjun, et al.
Published: (2024)

Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction
by: Nguyen, Thong, et al.
Published: (2023)

On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling
by: Wu, Xiaobao, et al.
Published: (2024)

Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation
by: Nguyen, Thong Thanh, et al.
Published: (2024)

Encoding and Controlling Global Semantics for Long-form Video Question Answering
by: Nguyen, Thong Thanh, et al.
Published: (2024)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
by: Xu, Huimin, et al.
Published: (2026)

More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
by: Vu, Duc Anh, et al.
Published: (2025)

Read as You See: Guiding Unimodal LLMs for Low-Resource Explainable Harmful Meme Detection
by: Pan, Fengjun, et al.
Published: (2025)

AKEW: Assessing Knowledge Editing in the Wild
by: Wu, Xiaobao, et al.
Published: (2024)

Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding
by: Nguyen, Thong, et al.
Published: (2025)

Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment
by: Nguyen, Cong-Duy, et al.
Published: (2023)

Unsupervised Hallucination Detection by Inspecting Reasoning Processes
by: Srey, Ponhvoan, et al.
Published: (2025)

Towards the TopMost: A Topic Modeling System Toolkit
by: Wu, Xiaobao, et al.
Published: (2023)

Curriculum Demonstration Selection for In-Context Learning
by: Vu, Duc Anh, et al.
Published: (2024)

Multi-Scale Contrastive Learning for Video Temporal Grounding
by: Nguyen, Thong Thanh, et al.
Published: (2024)

FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
by: Wu, Xiaobao, et al.
Published: (2024)

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
by: Srey, Ponhvoan, et al.
Published: (2026)

Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning
by: Wu, Xinyi, et al.
Published: (2025)

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
by: Wu, Xiaobao, et al.
Published: (2024)