An SDP-based algorithm estimates both control gains and minimum dwell times online for switched LQR systems with unknown dynamics, achieving O(|M|^{1/4} n_s^{3/4} + n_m) expected regret while keeping state norms bounded.
hub
Poisoning Attacks against Support Vector Machines
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
We investigate a family of poisoning attacks against Support Vector Machines (SVM). Such attacks inject specially crafted training data that increases the SVM's test error. Central to the motivation for these attacks is the fact that most learning algorithms assume that their training data comes from a natural or well-behaved distribution. However, this assumption does not generally hold in security-sensitive settings. As we demonstrate, an intelligent adversary can, to some extent, predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data. The proposed attack uses a gradient ascent strategy in which the gradient is computed based on properties of the SVM's optimal solution. This method can be kernelized and enables the attack to be constructed in the input space even for non-linear kernels. We experimentally demonstrate that our gradient ascent procedure reliably identifies good local maxima of the non-convex validation error surface, which significantly increases the classifier's test error.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
πCreds produces privacy-preserving verifiable credentials via trusted LLM inference on authenticated data, expanding claim types to unstructured sources and formalizing SCAE and ACPP threat models.
Use of model-generated content in training causes irreversible loss of distribution tails, termed model collapse, in VAEs, GMMs, and LLMs.
Gradient-guided rewiring of foreign-key edges in relational databases degrades GNN predictions on regression tasks while preserving schema integrity constraints.
Landseer offers a containerized modular system to integrate and evaluate combinations of machine learning defenses, with an initial analysis of 35 defenses highlighting replicability challenges.
Introduces Generative Privacy Funnel (GenPF) and deep variational PF (DVPF) models that extend the privacy funnel to generative settings and provide a controllable privacy-utility trade-off with reduced sensitive attribute leakage in face recognition.
Adversarial examples enable AI authority laundering by causing production VLMs to give authoritative but wrong responses on subtly perturbed images, with success rates of 22-100% using decade-old attack methods.
Clustering DINO representations via K-means and LDA filters poisoned speech samples, reducing attack success rate from 99.75% to 0.25% at 10% poisoning level.
FoggyTrust is a hierarchical extension of FLTrust that localizes trust computation to fog nodes and combines it with heterogeneity-aware optimizers, reporting over 50% gains on CIFAR-10 under Krum and Trim attacks.
Surveys indicate cybersecurity education correlates with higher concern for adversarial ML threats, and CTF-based challenges effectively engage students in learning about data poisoning attacks.
A Kubeflow-based MLOps architecture detects FGSM adversarial attacks on deployed AI models and automatically applies PGD-based adversarial training to recover accuracy.
DP2Guard is a proposed lightweight PPFL framework that combines gradient masking for privacy, hybrid anomaly detection via SVD and clustering for Byzantine robustness, trust-based adaptive aggregation, and blockchain logging for Industrial IoT.
Ensemble models like Random Forest and Gradient Boosting maintain more stable performance than Logistic Regression and Deep Neural Networks under label manipulation and outlier-based poisoning attacks on IoT intrusion detection datasets.
citing papers explorer
-
Regret-Guaranteed Safe Switching: LQR Setting with Unknown Dynamics
An SDP-based algorithm estimates both control gains and minimum dwell times online for switched LQR systems with unknown dynamics, achieving O(|M|^{1/4} n_s^{3/4} + n_m) expected regret while keeping state norms bounded.
-
$\pi$Creds: Privately Inferred Credentials
πCreds produces privacy-preserving verifiable credentials via trusted LLM inference on authenticated data, expanding claim types to unstructured sources and formalizing SCAE and ACPP threat models.
-
The Curse of Recursion: Training on Generated Data Makes Models Forget
Use of model-generated content in training causes irreversible loss of distribution tails, termed model collapse, in VAEs, GMMs, and LLMs.
-
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
Gradient-guided rewiring of foreign-key edges in relational databases degrades GNN predictions on regression tasks while preserving schema integrity constraints.
-
Landseer: Exploring the Machine Learning Defense Landscape
Landseer offers a containerized modular system to integrate and evaluate combinations of machine learning defenses, with an initial analysis of 35 defenses highlighting replicability challenges.
-
Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition
Introduces Generative Privacy Funnel (GenPF) and deep variational PF (DVPF) models that extend the privacy funnel to generative settings and provide a controllable privacy-utility trade-off with reduced sensitive attribute leakage in face recognition.
-
Laundering AI Authority with Adversarial Examples
Adversarial examples enable AI authority laundering by causing production VLMs to give authoritative but wrong responses on subtly perturbed images, with success rates of 22-100% using decade-old attack methods.
-
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System
Clustering DINO representations via K-means and LDA filters poisoned speech samples, reducing attack success rate from 99.75% to 0.25% at 10% poisoning level.
-
FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks
FoggyTrust is a hierarchical extension of FLTrust that localizes trust computation to fog nodes and combines it with heterogeneity-aware optimizers, reporting over 50% gains on CIFAR-10 under Krum and Trim attacks.
-
Comparative Insights on Adversarial Machine Learning from Industry and Academia: A User-Study Approach
Surveys indicate cybersecurity education correlates with higher concern for adversarial ML threats, and CTF-based challenges effectively engage students in learning about data poisoning attacks.
-
Enabling Adversarial Robustness in AI Models through Kubeflow MLOps
A Kubeflow-based MLOps architecture detects FGSM adversarial attacks on deployed AI models and automatically applies PGD-based adversarial training to recover accuracy.
-
DP2Guard: A Lightweight and Byzantine-Robust Privacy-Preserving Federated Learning Scheme for Industrial IoT
DP2Guard is a proposed lightweight PPFL framework that combines gradient masking for privacy, hybrid anomaly detection via SVD and clustering for Byzantine robustness, trust-based adaptive aggregation, and blockchain logging for Industrial IoT.
-
Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
Ensemble models like Random Forest and Gradient Boosting maintain more stable performance than Logistic Regression and Deep Neural Networks under label manipulation and outlier-based poisoning attacks on IoT intrusion detection datasets.
- Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness