Conic Certification of Transformer Attention
cs.LG, cs.AI, cs.CL, math.OC
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/chimera1001/conic-attention-cert
Terminology
Sources
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
- Layer Normalization
- Gaussian Error Linear Units (GELUs)
- Clarabel: An interior-point solver for conic programs with quadratic objectives
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