DETER: Suppression During Pretraining for Tamper Resistance
cs.LG
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/MEGlr/DETER
Terminology
Sources
- Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Muon is Scalable for LLM Training
- Shaping capabilities with token-level data filtering
- When Should We Introduce Safety Interventions During Pretraining?
- Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis