Cover Image

Jailbreak Transferability Emerges from Shared Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Angell, Rico, Brinkmann, Jannik, He, He
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training
by: Shah, Avidan, et al.
Published: (2026)

Polynomial Precision Dependence Solutions to Alignment Research Center Matrix Completion Problems
by: Angell, Rico
Published: (2024)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
by: Karvonen, Adam, et al.
Published: (2024)

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching
by: Angell, Rico, et al.
Published: (2023)

Estimating Tail Risks in Language Model Output Distributions
by: Angell, Rico, et al.
Published: (2026)

A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
by: Brinkmann, Jannik, et al.
Published: (2024)

In-Context Algebra
by: Todd, Eric, et al.
Published: (2025)

Representational Transfer Learning for Matrix Completion
by: He, Yong, et al.
Published: (2024)

Disentangling Shared and Task-Specific Representations from Multi-Modal Clinical Data
by: Lyu, He, et al.
Published: (2026)

Understanding and Enhancing the Transferability of Jailbreaking Attacks
by: Lin, Runqi, et al.
Published: (2025)

Mechanisms of AI Protein Folding in ESMFold
by: Lu, Kevin, et al.
Published: (2026)

Transfer Learning of Multiobjective Indirect Low-Thrust Trajectories Using Diffusion Models and Markov Chain Monte Carlo
by: Graebner, Jannik, et al.
Published: (2026)

On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
by: Han, Andy, et al.
Published: (2026)

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
by: Li, Songze, et al.
Published: (2026)

Trustworthy Transfer Learning: A Survey
by: Wu, Jun, et al.
Published: (2024)

FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
by: Lin, Runqi, et al.
Published: (2025)

The Environmental Impact of Ensemble Techniques in Recommender Systems
by: Nitschke, Jannik
Published: (2025)

SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
by: Mukherjee, Arpan, et al.
Published: (2025)

Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study
by: Li, Danya, et al.
Published: (2026)

Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks
by: Nurlanov, Zhakshylyk, et al.
Published: (2026)

Learning Shared Representations for Multi-Task Linear Bandits
by: Lin, Jiabin, et al.
Published: (2026)

Learning with Shared Representations: Statistical Rates and Efficient Algorithms
by: Niu, Xiaochun, et al.
Published: (2024)

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
by: Brinkmann, Jannik, et al.
Published: (2025)

Hierarchical Successor Representation for Robust Transfer
by: Yu, Changmin, et al.
Published: (2026)

Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations
by: Li, Kevin Y., et al.
Published: (2026)

Robust Knowledge Transfer in Tiered Reinforcement Learning
by: Huang, Jiawei, et al.
Published: (2023)

TRYLOCK: Defense-in-Depth Against LLM Jailbreaks via Layered Preference and Representation Engineering
by: Thornton, Scott
Published: (2026)

Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
by: Huang, Zixuan, et al.
Published: (2025)

Learning Shared Representations from Unpaired Data
by: Yacobi, Amitai, et al.
Published: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
by: Cui, Kaiyuan, et al.
Published: (2026)

Learning Relational Tabular Data without Shared Features
by: Wu, Zhaomin, et al.
Published: (2025)

Compound Fault Diagnosis for Train Transmission Systems Using Deep Learning with Fourier-enhanced Representation
by: Rico, Jonathan Adam, et al.
Published: (2025)

Towards Predicting the Success of Transfer-based Attacks by Quantifying Shared Feature Representations
by: Dale, Ashley S., et al.
Published: (2024)

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
by: Wurgaft, Daniel, et al.
Published: (2026)

Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems
by: Zangato, Théo, et al.
Published: (2026)

Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
by: Benhamza, Manal, et al.
Published: (2026)

Predictive Representations for Skill Transfer in Reinforcement Learning
by: Vereecken, Ruben, et al.
Published: (2026)

Understanding the Transferability of Representations via Task-Relatedness
by: Mehra, Akshay, et al.
Published: (2023)

Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
by: Miao, Albert, et al.
Published: (2025)

How Data Augmentation Shapes Neural Representations
by: He, Tianxiao, et al.
Published: (2026)