3 citations · 4 across the 4 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CL2025
Automatic Tensor-level Execution of Abstract Interpreters for Neural Networks
Avaljot Singh, Yasmin Chandini Sarita, Yamin Chandini Sarita +4
Developing new abstract interpretation-based DNN certifiers is difficult because their mathematical design is expressed at the neuron level, while implementations must operate at t…
cs.PL2025★ 3 cited
Automated Verification of Soundness of DNN Certifiers
Avaljot Singh, Yasmin Chandini Sarita, Charith Mendis +1
The uninterpretability of Deep Neural Networks (DNNs) hinders their use in safety-critical applications. Abstract Interpretation-based DNN certifiers provide promising avenues for…