Image de couverture de livre

Latent-space Attacks for Refusal Evasion in Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Piras, Giorgio, Mura, Raffaele, Brau, Fabio, Pintor, Maura, Oneto, Luca, Roli, Fabio, Biggio, Battista
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
par: Piras, Giorgio, et autres
Publié: (2025)

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
par: Mura, Raffaele, et autres
Publié: (2025)

S2AP: Score-space Sharpness Minimization for Adversarial Pruning
par: Piras, Giorgio, et autres
Publié: (2025)

HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks
par: Mura, Raffaele, et autres
Publié: (2024)

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
par: Piras, Giorgio, et autres
Publié: (2024)

Evaluating the Evaluators: Trust in Adversarial Robustness Tests
par: Cinà, Antonio Emanuele, et autres
Publié: (2025)

Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection
par: Ponte, Andrea, et autres
Publié: (2025)

Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning
par: Rossolini, Giulio, et autres
Publié: (2025)

SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network
par: Manca, Cristian, et autres
Publié: (2026)

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates
par: Angioni, Daniele, et autres
Publié: (2024)

Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
par: Gupta, Srishti, et autres
Publié: (2025)

Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
par: Guo, Wei, et autres
Publié: (2025)

Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models
par: Pintore, Marco, et autres
Publié: (2025)

Regression-aware Continual Learning for Android Malware Detection
par: Ghiani, Daniele, et autres
Publié: (2025)

SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines
par: Ponte, Andrea, et autres
Publié: (2024)

BlackCATT: Black-box Collusion Aware Traitor Tracing in Federated Learning
par: Rodríguez-Lois, Elena, et autres
Publié: (2026)

Empirical Quantification of Spurious Correlations in Malware Detection
par: Perasso, Bianca, et autres
Publié: (2025)

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
par: Cinà, Antonio Emanuele, et autres
Publié: (2024)

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches
par: Pintor, Maura, et autres
Publié: (2022)

On the Robustness of Adversarial Training Against Uncertainty Attacks
par: Ledda, Emanuele, et autres
Publié: (2024)

Prototype-Guided Robust Learning against Backdoor Attacks
par: Guo, Wei, et autres
Publié: (2025)

Nebula: Self-Attention for Dynamic Malware Analysis
par: Trizna, Dmitrijs, et autres
Publié: (2023)

Robust Synthetic Data-Driven Detection of Living-Off-the-Land Reverse Shells
par: Trizna, Dmitrijs, et autres
Publié: (2024)

Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking
par: Gupta, Srishti, et autres
Publié: (2025)

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
par: Gupta, Srishti, et autres
Publié: (2024)

Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
par: Rossolini, Giulio, et autres
Publié: (2022)

Label-efficient Training Updates for Malware Detection over Time
par: Minnei, Luca, et autres
Publié: (2026)

Energy-Latency Attacks via Sponge Poisoning
par: Cinà, Antonio Emanuele, et autres
Publié: (2022)

Evaluation of Audio Language Models for Fairness, Safety, and Security
par: Aloufi, Ranya, et autres
Publié: (2026)

Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
par: Demontis, Ambra, et autres
Publié: (2022)

LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries
par: Ren, Xuancheng, et autres
Publié: (2026)

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation
par: Shu, Huizhen, et autres
Publié: (2025)

Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering
par: Pintore, Marco, et autres
Publié: (2025)

A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classification
par: Zhang, Lu, et autres
Publié: (2024)

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
par: Gibert, Daniel, et autres
Publié: (2024)

A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification
par: Zhang, Lu, et autres
Publié: (2025)

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications
par: Zhang, Lu, et autres
Publié: (2025)

Countermeasures Against Adversarial Examples in Radio Signal Classification
par: Zhang, Lu, et autres
Publié: (2024)

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules
par: Pattison, Cameron, et autres
Publié: (2026)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
par: Kang, Mintong, et autres
Publié: (2023)