Cover Image

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shu, Huizhen, Li, Xuying, Wang, Qirui, Kosuga, Yuji, Tian, Mengqiu, Li, Zhuo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Output Length Effect on DeepSeek-R1's Safety in Forced Thinking
by: Li, Xuying, et al.
Published: (2025)

Precision Knowledge Editing: Enhancing Safety in Large Language Models
by: Li, Xuying, et al.
Published: (2024)

The Resurgence of GCG Adversarial Attacks on Large Language Models
by: Tan, Yuting, et al.
Published: (2025)

Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach
by: Li, Xuying, et al.
Published: (2025)

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation
by: Shu, Huizhen, et al.
Published: (2025)

Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation
by: Li, Xuying, et al.
Published: (2024)

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
by: Huang, Guanhua, et al.
Published: (2024)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
by: Li, Aaron J., et al.
Published: (2025)

Constrain Alignment with Sparse Autoencoders
by: Yin, Qingyu, et al.
Published: (2024)

SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
by: Liu, Dengcan, et al.
Published: (2025)

Sparse Autoencoders for Hypothesis Generation
by: Movva, Rajiv, et al.
Published: (2025)

Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups
by: Ghilardi, Davide, et al.
Published: (2024)

SAFER: Probing Safety in Reward Models with Sparse Autoencoder
by: Shi, Wei, et al.
Published: (2025)

Layer-Wise Evolution of Representations in Fine-Tuned Transformers: Insights from Sparse AutoEncoders
by: Nadipalli, Suneel
Published: (2025)

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization
by: Song, Shezheng, et al.
Published: (2025)

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations
by: Teja, Lekkala Sai, et al.
Published: (2025)

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
by: Fang, Yi, et al.
Published: (2026)

Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
by: Xiong, Guangzhi, et al.
Published: (2025)

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
by: O'Reilly, Cliff, et al.
Published: (2025)

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
by: Zhang, Ruikang, et al.
Published: (2026)

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
by: Wang, Hao, et al.
Published: (2026)

Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance
by: Tuck, Bryan E., et al.
Published: (2025)

Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation
by: Cao, Meng, et al.
Published: (2024)

LLMCache: Layer-Wise Caching Strategies for Accelerated Reuse in Transformer Inference
by: Bansal, Harsh Vardhan
Published: (2025)

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
by: Shu, Dong, et al.
Published: (2025)

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
by: Hu, Chenhui, et al.
Published: (2024)

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation
by: Lu, Yi, et al.
Published: (2025)

Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training
by: Baroian, Andrei, et al.
Published: (2025)

Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
by: Sim, Woo Seob, et al.
Published: (2026)

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
by: Yang, Yifei, et al.
Published: (2024)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
by: Taniguchi, Rei, et al.
Published: (2026)

A Generative Adversarial Attack for Multilingual Text Classifiers
by: Roth, Tom, et al.
Published: (2024)

Not All Layers of LLMs Are Necessary During Inference
by: Fan, Siqi, et al.
Published: (2024)

Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders
by: Xuan, Richmond Sin Jing, et al.
Published: (2025)

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
by: Chanin, David, et al.
Published: (2024)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2026)

Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume Optimization
by: Song, Junjie, et al.
Published: (2025)

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
by: Guo, Song, et al.
Published: (2024)

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
by: Shu, Dong, et al.
Published: (2025)

Multiscale Positive-Unlabeled Detection of AI-Generated Texts
by: Tian, Yuchuan, et al.
Published: (2023)