Search Results for author:
Found 21 papers, 7 papers with code
Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization
We propose a novel optimal attack formulation that considers the effect of the attack on the hyperparameters and models the attack as a multiobjective bilevel optimization problem.
Using 3D Shadows to Detect Object Hiding Attacks on Autonomous Vehicle Perception
We achieve this by searching for void regions and locating the obstacles that cause these shadows.
Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks
In this work, we propose a novel approach, Jacobian Ensembles-a combination of Jacobian regularization and model ensembles to significantly increase the robustness against UAPs whilst maintaining or improving model accuracy.
Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance.
Real-time Detection of Practical Universal Adversarial Perturbations
Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs).
Jacobian Regularization for Mitigating Universal Adversarial Perturbations
Universal Adversarial Perturbations (UAPs) are input perturbations that can fool a neural network on large sets of data.
Object Removal Attacks on LiDAR-based 3D Object Detectors
LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations.
Robustness and Transferability of Universal Attacks on Compressed Models
In this work, we analyze the effect of various compression techniques to UAP attacks, including different forms of pruning and quantization.
Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
We propose a novel optimal attack formulation that considers the effect of the attack on the hyperparameters by modelling the attack as a multiobjective bilevel optimisation problem.
Universal Adversarial Robustness of Texture and Shape-Biased Models
Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise.
Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets.
Poisoning Attacks with Generative Adversarial Nets
In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i. e. samples that look like genuine data points but that degrade the classifier's accuracy when used for training.
Sensitivity of Deep Convolutional Networks to Gabor Noise
Deep Convolutional Networks (DCNs) have been shown to be sensitive to Universal Adversarial Perturbations (UAPs): input-agnostic perturbations that fool a model on large portions of a dataset.
An Argumentation-Based Reasoner to Assist Digital Investigation and Attribution of Cyber-Attacks
In this work, we propose an argumentation-based reasoner (ABR) as a proof-of-concept tool that can help a forensics analyst during the analysis of forensic evidence and the attribution process.
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks
Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning algorithms at test time.
Mitigation of Adversarial Attacks through Embedded Feature Selection
We propose a design methodology to evaluate the security of machine learning classifiers with embedded feature selection against adversarial examples crafted using different attack strategies.
Label Sanitization against Label Flipping Poisoning Attacks
Label flipping attacks are a special case of data poisoning, where the attacker can control the labels assigned to a fraction of the training points.
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
We show empirically that the adversarial examples generated by these attack strategies are quite different from genuine points, as no detectability constrains are considered to craft the attack.
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
This exposes learning algorithms to the threat of data poisoning, i. e., a coordinate attack in which a fraction of the training data is controlled by the attacker and manipulated to subvert the learning process.
Argumentation-based Security for Social Good
The increase of connectivity and the impact it has in every day life is raising new and existing security problems that are becoming important for social good.
Efficient Attack Graph Analysis through Approximate Inference
We compare sequential and parallel versions of Loopy Belief Propagation with exact inference techniques for both static and dynamic analysis, showing the advantages of approximate inference techniques to scale to larger attack graphs.
