Provable Lipschitz Certification for Generative Models
We present a scalable technique for upper bounding the Lipschitz constant of generative models. We relate this quantity to the maximal norm over the set of attainable vector-Jacobian products of a given generative model. We approximate this set by layerwise convex approximations using zonotopes. Our approach generalizes and improves upon prior work using zonotope transformers and we extend to Lipschitz estimation of neural networks with large output dimension. This provides efficient and tight bounds on small networks and can scale to generative models on VAE and DCGAN architectures.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Provably Robust Adaptation for Language-Empowered Foundation Models
Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations, enabling powerful downstream capabilitie…
Few-Shot LearningCrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models
Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to la…
Semialgebraic Optimization for Lipschitz Constants of ReLU Networks
The Lipschitz constant of a network plays an important role in many applications of deep learning, such as robustness certification and Wasserstein Generative Adversarial Network. We introduce a semidefinite programming …
Adversarial RobustnessReward Certification for Policy Smoothed Reinforcement Learning
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed policies" in order to enhance its robustness. …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks
Data attribution methods identify which training examples are responsible for a model's predictions, but their sensitivity to distributional perturbations undermines practical reliability. We present a unified framework …
Anomaly Detection