Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
Mauro Conti, Ankit Gangwal, Aaryan Ajay Sharma
cs.LG
Submitted: 2026-08-20
Updated: 2026-08-21
Terminology
Sources
- AdaMerging: Adaptive Model Merging for Multi-Task Learning
- Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
- Intriguing properties of neural networks
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- On Evaluating Adversarial Robustness
- The Space of Transferable Adversarial Examples
- Explaining and Harnessing Adversarial Examples
- Adam: A Method for Stochastic Optimization
- LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
- SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
- Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks