Search Results - "Gehr, Timon"

AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation by Gehr, Timon, Mirman, Matthew, Drachsler-Cohen, Dana, Tsankov, Petar, Chaudhuri, Swarat, Vechev, Martin

“…We present AI 2 , the first sound and scalable analyzer for deep neural networks. Based on overapproximation, AI 2 can automatically prove safety properties…”
Get full text

AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs by Ünsal, Mert, Gehr, Timon, Vechev, Martin

“…We present the first correct-by-construction learning-based system for step-by-step mathematical integration. The key idea is to learn a policy, represented by…”
Get full text

Modular Synthesis of Efficient Quantum Uncomputation by Venev, Hristo, Gehr, Timon, Dimitrov, Dimitar, Vechev, Martin

“…A key challenge of quantum programming is uncomputation: the reversible deallocation of qubits. And while there has been much recent progress on automating…”
Get full text

Robustness Certification of Generative Models by Mirman, Matthew, Gehr, Timon, Vechev, Martin

“…Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images…”
Get full text

Provably Robust Adversarial Examples by Dimitrov, Dimitar I, Singh, Gagandeep, Gehr, Timon, Vechev, Martin

“…We introduce the concept of provably robust adversarial examples for deep neural networks - connected input regions constructed from standard adversarial…”
Get full text