Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

25497498 · Jun 202019922001200920172026
48 results for aggregation defenses

Aggregation defenses improve deep learning models' robustness against data poisoning attacks.

problem Data poisoning attacks manipulate deep learning models with malicious training samples.
method Deep Partition Aggregation, efficiency improvements, data-to-complexity ratio, poisoning overfitting phenomenon.
result Aggregation defenses boost poisoning robustness through the poisoning overfitting phenomenon.

Improved defense against data poisoning attacks by aggregating smaller subsets.

problem Mitigating the impact of poisoned data on model robustness.
method Finite Aggregation method that combines duplicates of smaller disjoint subsets for training.
result Consistent improvement in certified robustness bounds, up to 4.77% on GTSRB.

Deep Partition Aggregation defends against poisoning attacks with provable certificates.

problem Adversarial poisoning attacks corrupt classifier test-time behavior.
method Deep Partition Aggregation (DPA) is an ensemble method using hash partitions and base models trained on these partitions.
result DPA can certify >= 50% of test images against over 500 poison image insertions on MNIST, and nine insertions on CIFAR-10.

A new method aggregates generative classifiers to resist adversarial attacks.

problem Adversarial attacks on deep neural networks.
method Rank-aggregating ensemble of generative classifiers trained on intermediate layer responses.
result The ensemble of generative classifiers shows robustness to adversarial attacks.

FDA3 defends IIoT applications against adversarial attacks by federating defense knowledge.

problem Adversarial attacks on DNNs in IIoT applications can cause devastating consequences.
method Federated learning approach to aggregate defense knowledge from different sources.
result FDA3 can resist more attacks than existing methods and prevent new attacks.

PatchGuard defends against localized adversarial patches with provable robustness.

problem Localized adversarial patches induce misclassification in machine learning models.
method PatchGuard uses CNNs with small receptive fields and robust masking to detect and mask corrupted features.
result PatchGuard achieves state-of-the-art provable robust accuracy and clean accuracy.

Federated learning is vulnerable to backdoor attacks; a new defense method is proposed.

problem Backdoor attacks in federated learning that can misclassify models.
method Adjusting the learning rate based on sign information of agents' updates.
result Our defense significantly reduces or eliminates backdoor attacks in federated learning.

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …

2019-05-09abs ↗pdf ↗

New aggregation method improves GNN robustness to structural perturbations.

problem Graph Neural Networks (GNNs) are vulnerable to adversarial attacks that manipulate graph structure.
method Proposes a robust aggregation function with a breakdown point of 0.5, inspired by robust statistics.
result Improves GNN robustness by a factor of 3 on Cora ML and 5.5 on Citeseer, and 8 for low-degree nodes.

Simple aggregation of multiple methods defends against adversarial attacks on neural networks.

problem Manipulation of machine learning models to hide discriminating features.
method Aggregation of multiple explanation methods to make the model robust against adversarial attacks.
result The model remains robust even when the attacker has knowledge of the model weights and explanation methods.

Federated learning is a recently proposed paradigm that enables multiple clients to collaboratively train a joint model. It allows clients to train models locally, and leverages the parameter server to generate a global model by aggregating the locally submitted gradient updates at each round. Although the incentive mo…

2019-11-28abs ↗pdf ↗

Paper defends sensitive attributes in GNNs from inference attacks.

problem Protecting sensitive attributes in GNNs from inference attacks.
method Proposes adversarial training with TV and Wasserstein distance to locally filter sensitive attributes.
result Framework creates strong defense against inference attacks with minimal performance loss.

FLANDERS detects and blocks extreme model poisoning in federated learning.

problem Resilience against large-scale model poisoning attacks in federated learning.
method FLANDERS treats client updates as matrix-valued time series and identifies outliers using autoregressive forecasting.
result FLANDERS significantly improves robustness in federated learning across various attacks.

New defense method inspired by encryption improves visual classification accuracy.

problem Conventional defenses reduce accuracy and are defeated by obfuscated gradients.
method Block-wise pixel shuffling with secret key for training and test images.
result Achieves high accuracy (91.55%) on clean images and (89.66%) on adversarial examples.

Automated discovery of adaptive attacks improves adversarial defense evaluation.

problem Challenges in reliably evaluating adversarial defenses.
method Formalizes adaptive attacks as reusable building blocks in a search space for automatic discovery.
result Our tool discovers significantly stronger attacks than AutoAttack, improving adversarial defense evaluation.

Unified framework analyzes privacy risks from gradients in distributed learning.

problem Analyzing inference privacy risks from gradients in machine learning.
method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.
result Demonstrates inefficacy of data aggregation for privacy against inference attacks.

New research shows many recent defenses against adversarial examples are ineffective against black-box attacks.

problem The robustness of recent defenses against adversarial examples is insufficient, especially against black-box attacks.
method Evaluation of nine defenses on two black-box adversarial models and six attacks on CIFAR-10 and Fashion-MNIST datasets.
result Most recent defenses provide only marginal improvements in security (<25%<25\%) compared to undefended networks.

SmoothLLM defends LLMs from jailbreaking attacks by randomly perturbing inputs.

problem Adversaries can fool large language models into generating objectionable content.
method SmoothLLM randomly perturbs multiple copies of a prompt and aggregates predictions to detect adversarial inputs.
result SmoothLLM sets the state-of-the-art for robustness against various jailbreak attacks.

Heterophily affects GNN robustness; separating ego- and neighbor-embeddings improves defense.

problem The robustness of GNNs to adversarial attacks.
method Formalized relation between heterophily and GNN robustness; empirical analysis; design principles for improved robustness.
result Separating ego- and neighbor-embeddings increases GNN robustness.

Paper analyzes adversarial attacks and defenses using game theory.

problem Unclear conditions for optimal attacks and defenses in adversarial learning.
method Game-theoretic framework with locally linear decision boundary model.
result Fast Gradient Method attack and Randomized Smoothing defense form a Nash Equilibrium.

This study evaluates adversarial attacks and defenses for chest X-ray disease classification.

problem Vulnerability of deep neural networks to adversarial examples in chest X-ray disease detection.
method Detailed introduction and evaluation of various attack and defense methods.
result Attack and defense methods perform poorly with excessive iterations and large perturbations.

Stochastic defense improves natural classifiers against adversarial attacks.

problem Vulnerability of deep networks to adversarial attacks.
method Long-run MCMC sampling with Energy-Based Model for adversarial purification.
result Balancing memoryless and metastable behavior leads to effective purification and robust classification.

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of prior work has developed attacks and defenses, there is not much general understan…

2019-05-28abs ↗pdf ↗

Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect. We believe a large contri…

2019-02-18abs ↗pdf ↗