Cover Image

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Baker, Mohammed Abu, Babu-Saheer, Lakshmi
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
by: Das, Anindya Sundar, et al.
Published: (2025)

Composite Backdoor Attacks Against Large Language Models
by: Huang, Hai, et al.
Published: (2023)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
by: Xu, Jiashu, et al.
Published: (2023)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
by: Cho, Hakaze, et al.
Published: (2025)

Mechanistic Anomaly Detection for "Quirky" Language Models
by: Johnston, David O., et al.
Published: (2025)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
by: Yan, Jun, et al.
Published: (2023)

SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
by: Xue, Eric, et al.
Published: (2025)

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
by: Shang, Bingqi, et al.
Published: (2025)

Eliminating Position Bias of Language Models: A Mechanistic Approach
by: Wang, Ziqi, et al.
Published: (2024)

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
by: Huo, Yifu, et al.
Published: (2026)

Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models
by: Binkowski, Jakub, et al.
Published: (2026)

How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective
by: Peng, Runyu, et al.
Published: (2026)

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
by: Min, Nay Myat, et al.
Published: (2024)

Disentangling Exploration of Large Language Models by Optimal Exploitation
by: Grams, Tim, et al.
Published: (2025)

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
by: Yu, Zhongzhi, et al.
Published: (2024)

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
by: Liu, Runze, et al.
Published: (2025)

Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
by: Tan, Wenhui, et al.
Published: (2026)

How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective
by: Liu, Qi, et al.
Published: (2025)

Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
by: Lamparth, Max, et al.
Published: (2023)

On the Impact of Language Nuances on Sentiment Analysis with Large Language Models: Paraphrasing, Sarcasm, and Emojis
by: Bhargava, Naman, et al.
Published: (2025)

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
by: Son, Seungwoo, et al.
Published: (2024)

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
by: Kiruluta, Andrew
Published: (2026)

Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention
by: Gao, Bin, et al.
Published: (2024)

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
by: He, Jinghan, et al.
Published: (2024)

Z-Pruner: Post-Training Pruning of Large Language Models for Efficiency without Retraining
by: Bhuiyan, Samiul Basir, et al.
Published: (2025)

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
by: He, Jiaming, et al.
Published: (2024)

LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics
by: Tang, Jialiang, et al.
Published: (2025)

Test-Time Backdoor Attacks on Multimodal Large Language Models
by: Lu, Dong, et al.
Published: (2024)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
by: Huang, Yanwen, et al.
Published: (2025)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
by: Tyukin, Georgy, et al.
Published: (2024)

Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models
by: kurra, Sailesh kiran, et al.
Published: (2026)

Exploring Activation Patterns of Parameters in Language Models
by: Wang, Yudong, et al.
Published: (2024)

Deep Learning Detection Method for Large Language Models-Generated Scientific Content
by: Alhijawi, Bushra, et al.
Published: (2024)

Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition
by: Duan, Yifei, et al.
Published: (2025)

Sliding Window Attention Training for Efficient Large Language Models
by: Fu, Zichuan, et al.
Published: (2025)

Instruction Following by Principled Boosting Attention of Large Language Models
by: Guardieiro, Vitoria, et al.
Published: (2025)

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
by: Dai, Runpeng, et al.
Published: (2025)

Attention-Based Sampler for Diffusion Language Models
by: Zhou, Yuyan, et al.
Published: (2026)

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
by: Liu, Qin, et al.
Published: (2024)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
by: Lin, Huawei, et al.
Published: (2025)