ADS-C: Antidistillation Sampling for Classification
Khawaja Abaid Ullah, Mohammad Javad Khojasteh
cs.LG, cs.CR
Submitted: 2026-07-16
Comments: 20 pages, 28 figures
Code: https://github.com/the-kaslab/ADS-C
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- Deep Intellectual Property Protection: A Survey
- ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
- Antidistillation Sampling
- Understanding and Improving Knowledge Distillation
- Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMs
- A Survey on Knowledge Distillation of Large Language Models
- Undistillable: Making A Nasty Teacher That CANNOT teach students
- MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
- MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks
- Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
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