Security Properties of Neural Networks as Decision Problems
cs.LO, cs.CC, cs.CR, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Dynamic Toolbox for ETRINV
- Framework for $\exists \mathbb{R}$-Completeness of Two-Dimensional Packing Problems
- The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Verifying Neural Networks Against Backdoor Attacks
- Random Parameter Noise Does Not Make Exact ReLU Verification Easy
- Checking extracted rules in Neural Networks
Related papers
- An Information-Flow Perspective on Explainability Requirements: Specification and Verification
- A programming language combining quantum and classical control
- Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows
- Encoder-Decoder Transformers: Logical Characterizations and Periodicity
- Ultraconstructive Model Theory via Bounded Adversarial Finite Structures