Cover Image

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Piras, Giorgio, Mura, Raffaele, Brau, Fabio, Oneto, Luca, Roli, Fabio, Biggio, Battista
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Latent-space Attacks for Refusal Evasion in Language Models
by: Piras, Giorgio, et al.
Published: (2026)

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
by: Mura, Raffaele, et al.
Published: (2025)

S2AP: Score-space Sharpness Minimization for Adversarial Pruning
by: Piras, Giorgio, et al.
Published: (2025)

Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning
by: Rossolini, Giulio, et al.
Published: (2025)

HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks
by: Mura, Raffaele, et al.
Published: (2024)

SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network
by: Manca, Cristian, et al.
Published: (2026)

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
by: Piras, Giorgio, et al.
Published: (2024)

Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection
by: Ponte, Andrea, et al.
Published: (2025)

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates
by: Angioni, Daniele, et al.
Published: (2024)

Evaluating the Evaluators: Trust in Adversarial Robustness Tests
by: Cinà, Antonio Emanuele, et al.
Published: (2025)

Nebula: Self-Attention for Dynamic Malware Analysis
by: Trizna, Dmitrijs, et al.
Published: (2023)

Robust Synthetic Data-Driven Detection of Living-Off-the-Land Reverse Shells
by: Trizna, Dmitrijs, et al.
Published: (2024)

Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
by: Gupta, Srishti, et al.
Published: (2025)

On the Robustness of Adversarial Training Against Uncertainty Attacks
by: Ledda, Emanuele, et al.
Published: (2024)

Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024)

Regression-aware Continual Learning for Android Malware Detection
by: Ghiani, Daniele, et al.
Published: (2025)

On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration
by: Petrov, Valentin
Published: (2026)

A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification
by: Zhang, Lu, et al.
Published: (2025)

SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines
by: Ponte, Andrea, et al.
Published: (2024)

Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models
by: Pintore, Marco, et al.
Published: (2025)

Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking
by: Gupta, Srishti, et al.
Published: (2025)

Two Heads Are Better than One: Simulating Large Transformers with Small Ones
by: Yu, Hantao, et al.
Published: (2025)

Energy-Latency Attacks via Sponge Poisoning
by: Cinà, Antonio Emanuele, et al.
Published: (2022)

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
by: Muhamed, Aashiq, et al.
Published: (2025)

Empirical Quantification of Spurious Correlations in Malware Detection
by: Perasso, Bianca, et al.
Published: (2025)

Towards One-shot Federated Learning: Advances, Challenges, and Future Directions
by: Amato, Flora, et al.
Published: (2025)

Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices
by: Zhang, Lu, et al.
Published: (2025)

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
by: Rahimi, Eliron, et al.
Published: (2026)

Hyperbolic Learning with Multimodal Large Language Models
by: Mandica, Paolo, et al.
Published: (2024)

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
by: Gupta, Srishti, et al.
Published: (2024)

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches
by: Pintor, Maura, et al.
Published: (2022)

On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
by: Alberghi, Riccardo, et al.
Published: (2025)

Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
by: Zhou, Zhanhui, et al.
Published: (2023)

DirectMultiStep: Direct Route Generation for Multistep Retrosynthesis
by: Shee, Yu, et al.
Published: (2024)

Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes
by: Trapasso, Alessandro, et al.
Published: (2025)

CIVeX: Causal Intervention Verification for Language Agents
by: Rovai, Fabio
Published: (2026)

Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks
by: Lyu, Xingyu, et al.
Published: (2025)

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
by: Yang, Puning, et al.
Published: (2026)

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
by: Chen, Zhikang, et al.
Published: (2025)

SatSOM: Saturation Self-Organizing Maps for Continual Learning
by: Urbanik, Igor, et al.
Published: (2025)