SLiR parameterizes linear relaxations by slope and uses shifting to compute sound bounds for general activation functions, enabling up to 7.8x more verified properties than prior methods.
The third international verification of neural networks competition (VNN-COMP 2022): Summary and results,
4 Pith papers cite this work, alongside 28 external citations. Polarity classification is still indexing.
4
Pith papers citing it
28
external citations · external index
years
2026 4verdicts
UNVERDICTED 4representative citing papers
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
diffRL enables verification of symbolic properties over input ranges for DRL agents in adaptive video streaming, wireless resource management, and congestion control by decomposing them into tractable sub-properties for existing DNN verifiers.
Adapts TP and FSDP to bound-propagation verification, with FSDP delivering bitwise-identical bounds and 80-90% baseline memory reduction while TP trades some tightness for ~2x peak-memory savings.
citing papers explorer
-
Shifting-based Optimizable Linear Relaxations for General Activation Functions
SLiR parameterizes linear relaxations by slope and uses shifting to compute sound bounds for general activation functions, enabling up to 7.8x more verified properties than prior methods.
-
Quantitative Linear Logic for Neuro-Symbolic Learning and Verification
QLL is a novel logic for neuro-symbolic learning that uses ML-native operations (sum, log-sum-exp) on logits to embed constraints, satisfying most linear logic properties and showing stronger correlation between empirical robustness and formal verification than prior approaches.
-
Analyzing Symbolic Properties for DRL Agents in Systems and Networking
diffRL enables verification of symbolic properties over input ranges for DRL agents in adaptive video streaming, wireless resource management, and congestion control by decomposing them into tractable sub-properties for existing DNN verifiers.
-
Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism
Adapts TP and FSDP to bound-propagation verification, with FSDP delivering bitwise-identical bounds and 80-90% baseline memory reduction while TP trades some tightness for ~2x peak-memory savings.