Cover Image

Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yang, Xiao, Chenghao, Li, Yizhi, Middleton, Stuart E., Moubayed, Noura Al, Lin, Chenghua
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
by: Wang, Yang, et al.
Published: (2025)

Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification
by: Wang, Yang, et al.
Published: (2023)

RAR-b: Reasoning as Retrieval Benchmark
by: Xiao, Chenghao, et al.
Published: (2024)

X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation
by: Zhao, Kun, et al.
Published: (2024)

Pixel Sentence Representation Learning
by: Xiao, Chenghao, et al.
Published: (2024)

MuLD: The Multitask Long Document Benchmark
by: Hudson, G Thomas, et al.
Published: (2022)

Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning
by: Slack, Dean L., et al.
Published: (2025)

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations
by: Xiao, Chenghao, et al.
Published: (2025)

SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
by: Wu, Siwei, et al.
Published: (2024)

Interpreting Adversarial Attacks and Defences using Architectures with Enhanced Interpretability
by: Rao, Akshay G, et al.
Published: (2025)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
by: Lyu, Saiyue, et al.
Published: (2024)

Everything is a Video: Unifying Modalities through Next-Frame Prediction
by: Hudson, G. Thomas, et al.
Published: (2024)

Evaluating Defences against Unsafe Feedback in RLHF
by: Rosati, Domenic, et al.
Published: (2024)

On the Rigour of Scientific Writing: Criteria, Analysis, and Insights
by: James, Joseph, et al.
Published: (2024)

Round Trip Translation Defence against Large Language Model Jailbreaking Attacks
by: Yung, Canaan, et al.
Published: (2024)

LLMs for LLMs: A Structured Prompting Methodology for Long Legal Documents
by: Klem, Strahinja, et al.
Published: (2025)

Effective Distillation of Table-based Reasoning Ability from LLMs
by: Yang, Bohao, et al.
Published: (2023)

Representation Noising: A Defence Mechanism Against Harmful Finetuning
by: Rosati, Domenic, et al.
Published: (2024)

Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level
by: Zeng, Xinyi, et al.
Published: (2024)

MIEB: Massive Image Embedding Benchmark
by: Xiao, Chenghao, et al.
Published: (2025)

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
by: Leask, Patrick, et al.
Published: (2025)

On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models
by: Yang, April, et al.
Published: (2024)

Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
by: Hong, Hanhua, et al.
Published: (2025)

Evaluating Large Language Models for Generalization and Robustness via Data Compression
by: Li, Yucheng, et al.
Published: (2024)

RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation
by: James, Joseph, et al.
Published: (2026)

Assessing Adversarial Robustness of Large Language Models: An Empirical Study
by: Yang, Zeyu, et al.
Published: (2024)

Robustness of Large Language Models Against Adversarial Attacks
by: Tao, Yiyi, et al.
Published: (2024)

Overview of the NLPCC 2024 Shared Task on Chinese Metaphor Generation
by: Qu, Xingwei, et al.
Published: (2024)

Overview of the NLPCC 2025 Shared Task: Gender Bias Mitigation Challenge
by: Li, Yizhi, et al.
Published: (2025)

CAST: Corpus-Aware Self-similarity Enhanced Topic modelling
by: Ma, Yanan, et al.
Published: (2024)

Defence Technology
Published: (2015)

BioMNER: A Dataset for Biomedical Method Entity Recognition
by: Tang, Chen, et al.
Published: (2024)

AttenCraft: Attention-guided Disentanglement of Multiple Concepts for Text-to-Image Customization
by: Shentu, Junjie, et al.
Published: (2024)

Textual Localization: Decomposing Multi-concept Images for Subject-Driven Text-to-Image Generation
by: Shentu, Junjie, et al.
Published: (2024)

Enhancing Language Agent Strategic Reasoning through Self-Play in Adversarial Games
by: Zhang, Yikai, et al.
Published: (2025)

PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
by: Zhang, Tianrong, et al.
Published: (2024)

Defensive Dual Masking for Robust Adversarial Defense
by: Yang, Wangli, et al.
Published: (2024)

Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification
by: Steigerwald, Philipp, et al.
Published: (2026)

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
by: Zheng, Yujia, et al.
Published: (2025)

Natural Language Generation
by: van Miltenburg, Emiel, et al.
Published: (2025)