Hardware faults can flip bits in the stored weights of a quantized neural network, potentially compromising its predictions. While such faults typically affect multiple parameters simultaneously, existing verifiers are limited to single-parameter perturbations due to the combinatorial explosion of possible flip locatio...
Hai Duong, Thanh Le, H. Nguyen et al.· 0 citations
Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharply under adversarial perturbations and channel disturbances; no method formally bounds this degradation for DeepJSCC. We present the first bound-propag...
Thanh Le, Hai Duong, Takeshi Matsumura et al.· 0 citations
Constrained Lagrangian Abstract Domain (CLAD), a new abstract domain that computes a sound over-approximation of neural networks over input regions defined by a combination of convex constraints, is introduced.
Formal verification can play a key role in ensuring the reliability of Deep Neural Networks (DNNs) deployed in safety-critical systems. Modern DNN verifiers employ a branch-and-bound framework, which alternates between branching (splitting into smaller subproblems) and bounding (pruning subproblems) to efficiently expl...
ZonoGpt, an abstract domain for verifying large transformers that maintains a space complexity independent of network depth, is introduced, an abstract domain for verifying large transformers that maintains a space complexity independent of network depth.
Hai Duong, Thanh Le, Thanhvu Nguyen· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
