Copertina

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dombrowski, Ann-Kathrin, Bowen, Dillon, Gleave, Adam, Cundy, Chris
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computers and Society Machine Learning 68T07
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations
di: Bowen, Dillon, et al.
Pubblicazione: (2025)

A Human-In-The-Loop Approach for Improving Fairness in Predictive Business Process Monitoring
di: Käppel, Martin, et al.
Pubblicazione: (2025)

Trajectory-Aware Reliability Modeling of Democratic Systems
di: Zaytsev, Dmitry, et al.
Pubblicazione: (2026)

A Generalization Bound for a Family of Implicit Networks
di: Fung, Samy Wu, et al.
Pubblicazione: (2024)

Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
di: Pavlov, Gorgi
Pubblicazione: (2026)

Preference Learning with Lie Detectors can Induce Honesty or Evasion
di: Cundy, Chris, et al.
Pubblicazione: (2025)

On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing
di: Behboodi, Arash, et al.
Pubblicazione: (2024)

Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach
di: Liu, Linyu, et al.
Pubblicazione: (2024)

Optimizing MoE Routers: Design, Implementation, and Evaluation in Transformer Models
di: Harvey, Daniel Fidel, et al.
Pubblicazione: (2025)

Improving Fairness and Mitigating MADness in Generative Models
di: Mayer, Paul, et al.
Pubblicazione: (2024)

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
di: Liu, Qiang, et al.
Pubblicazione: (2026)

Two-Stage Generative Model for Intracranial Aneurysm Meshes with Morphological Marker Conditioning
di: Ding, Wenhao, et al.
Pubblicazione: (2025)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
di: Yamchote, Phaphontee, et al.
Pubblicazione: (2025)

Wave-Attractor-Tree: A Hierarchical Binary Tree Reduction Architecture for Efficient Sequence Modeling
di: Berezkin, Igor
Pubblicazione: (2026)

Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models
di: Yang, Hong, et al.
Pubblicazione: (2026)

Nonlinear GENERIC Informed Neural Networks (N-GINNs): learning GENERIC dynamics with non-quadratic dissipation potentials
di: Votruba, Vojtěch, et al.
Pubblicazione: (2026)

Attention to Mamba: A Recipe for Cross-Architecture Distillation
di: Moudgil, Abhinav, et al.
Pubblicazione: (2026)

Feature Selection with Annealing for Forecasting Financial Time Series
di: Pabuccu, Hakan, et al.
Pubblicazione: (2023)

The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
di: Brännvall, Rickard, et al.
Pubblicazione: (2023)

A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms
di: Yazdanjue, Navid, et al.
Pubblicazione: (2025)

The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
di: Bastounis, Alexander, et al.
Pubblicazione: (2023)

Graph-Conditional Flow Matching for Relational Data Generation
di: Scassola, Davide, et al.
Pubblicazione: (2025)

Feature Learning Beyond the Edge of Stability
di: Terjék, Dávid
Pubblicazione: (2025)

Optimizing Basis Function Selection in Constructive Wavelet Neural Networks and Its Applications
di: Huang, Dunsheng, et al.
Pubblicazione: (2025)

A Teacher-Student Perspective on the Dynamics of Learning Near the Optimal Point
di: Couto, Carlos, et al.
Pubblicazione: (2025)

Closed-Form Feedback-Free Learning with Forward Projection
di: O'Shea, Robert, et al.
Pubblicazione: (2025)

Markov Chain Estimation with In-Context Learning
di: Lepage, Simon, et al.
Pubblicazione: (2025)

Structured Knowledge Accumulation: The Principle of Entropic Least Action in Forward-Only Neural Learning
di: Quantiota, Bouarfa Mahi
Pubblicazione: (2025)

Iterative Orthogonalization Scaling Laws
di: Selvaraj, Devan
Pubblicazione: (2025)

MLPs at the EOC: Spectrum of the NTK
di: Terjék, Dávid, et al.
Pubblicazione: (2025)

Segmentation of cracks in 3d images of fiber reinforced concrete using deep learning
di: Nowacka, Anna, et al.
Pubblicazione: (2025)

Deep generative models as the probability transformation functions
di: Bondar, Vitalii, et al.
Pubblicazione: (2025)

MLPs at the EOC: Concentration of the NTK
di: Terjék, Dávid, et al.
Pubblicazione: (2025)

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
di: Liu, Qiang, et al.
Pubblicazione: (2024)

A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets
di: Tavakoli, Fatemeh, et al.
Pubblicazione: (2023)

Deep Learning and Transfer Learning Architectures for English Premier League Player Performance Forecasting
di: Frees, Daniel, et al.
Pubblicazione: (2024)

Flow matching on homogeneous spaces
di: Ruscelli, Francesco
Pubblicazione: (2026)

Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization
di: Qin, Zhou, et al.
Pubblicazione: (2024)

Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs
di: Chowdhury, Soutrik Roy
Pubblicazione: (2024)

Training-Free Generative Sampling via Moment-Matched Score Smoothing
di: Yao, Zhenyu, et al.
Pubblicazione: (2026)