SensorFault-Bench is a new CPS-grounded benchmark showing that clean-MSE rankings of forecasting models often disagree with their robustness under standardized sensor-fault scenarios across four real datasets.
Towards deep learning models resistant to adversarial attacks
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
method 2
citation-polarity summary
representative citing papers
PGD²-GSM is the first method to stably achieve high-resolution global semantic manipulation in learned image compression via a Periodic Geometric Decay schedule that handles Lazying-Oscillating-Refining attack stages.
A framework models DNN layer weight-activation interactions via Bernoulli distributions and uses class separation as a diagnostic proxy to quantify distributional robustness, tested on CIFAR-10 and ImageNet models.
Penalty-based first-order methods find ε-KKT points in bilevel minimax problems with Õ(ε^{-4}) deterministic and Õ(ε^{-9}) stochastic oracle complexity, improving prior bounds for constrained lower-level cases via Lagrangian duality.
Negative-capable ridge regression uses controlled negative regularization as anti-shrinkage to increase effective complexity along weak eigendirections and mitigate underfitting in small-data regression.
AGC is a training-free inference-time defense for CLIP that adaptively corrects features along geodesics to robust augmentations, claiming 44.4% higher average robust accuracy and 10x lower latency than prior baselines across eight datasets and three backbones.
A game-theoretic framework and algorithms are introduced to maximize beneficial information from ML systems while minimizing biased influences arising from conflicts of interest.
FragileFlow formalizes margin-aware error flow and applies spectral control through a calibrated margin buffer and class-wise risk matrix, supported by a PAC-Bayes bound, to enhance worst-class robustness in foundation model adaptation while preserving clean accuracy.
MEFA enables exact full-gradient white-box attacks on iterative stochastic purification defenses like diffusion and Langevin EBMs by trading recomputation for lower memory, revealing vulnerabilities missed by approximate-gradient methods.
citing papers explorer
-
Benchmarking Sensor-Fault Robustness in Forecasting
SensorFault-Bench is a new CPS-grounded benchmark showing that clean-MSE rankings of forecasting models often disagree with their robustness under standardized sensor-fault scenarios across four real datasets.
-
Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression
PGD²-GSM is the first method to stably achieve high-resolution global semantic manipulation in learned image compression via a Periodic Geometric Decay schedule that handles Lazying-Oscillating-Refining attack stages.
-
A New Framework to Analyse the Distributional Robustness of Deep Neural Networks
A framework models DNN layer weight-activation interactions via Bernoulli distributions and uses class separation as a diagnostic proxy to quantify distributional robustness, tested on CIFAR-10 and ImageNet models.
-
Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
Penalty-based first-order methods find ε-KKT points in bilevel minimax problems with Õ(ε^{-4}) deterministic and Õ(ε^{-9}) stochastic oracle complexity, improving prior bounds for constrained lower-level cases via Lagrangian duality.
-
A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization
Negative-capable ridge regression uses controlled negative regularization as anti-shrinkage to increase effective complexity along weak eigendirections and mitigate underfitting in small-data regression.
-
AGC: Adaptive Geodesic Correction for Adversarial Robustness on Vision-Language Models
AGC is a training-free inference-time defense for CLIP that adaptively corrects features along geodesics to robust augmentations, claiming 44.4% higher average robust accuracy and 10x lower latency than prior baselines across eight datasets and three backbones.
-
Learning with Conflicts of Interest
A game-theoretic framework and algorithms are introduced to maximize beneficial information from ML systems while minimizing biased influences arising from conflicts of interest.
-
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
FragileFlow formalizes margin-aware error flow and applies spectral control through a calibrated margin buffer and class-wise risk matrix, supported by a PAC-Bayes bound, to enhance worst-class robustness in foundation model adaptation while preserving clean accuracy.
-
Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations
MEFA enables exact full-gradient white-box attacks on iterative stochastic purification defenses like diffusion and Langevin EBMs by trading recomputation for lower memory, revealing vulnerabilities missed by approximate-gradient methods.