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.
New framework detects and removes malicious model updates in federated learning.
Data poisoning attacks can severely degrade FL models, especially targeting specific classes.
Paper proposes efficient privacy-preserving matrix encryption for secure collaborative learning against malicious adversaries.
Efficient active learning method defends against malicious mislabeling and data poisoning attacks.
Malicious agents can manipulate linear contextual bandits to pull desired arms with logarithmic overhead.
Bayesian framework robustifies classifiers against malicious attacks.
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided bas…
The devastating effects of cyber-attacks, highlight the need for novel attack detection and prevention techniques. Over the last years, considerable work has been done in the areas of attack detection as well as in collaborative defense. However, an analysis of the state of the art suggests that many challenges exist i…
FLANDERS detects and blocks extreme model poisoning in federated learning.
On the path to establishing a global cybersecurity framework where each enterprise shares information about malicious behavior, an important question arises. How can a machine learning representation characterizing a cyber attack on one network be used to detect similar attacks on other enterprise networks if each netw…
BadGD identifies gradient descent vulnerabilities through strategic backdoor attacks.
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this work, we explore the threat of model poisoning attacks on federated learning initia…
FDA3 defends IIoT applications against adversarial attacks by federating defense knowledge.
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-…
Optimal policies identified for learning systems with a malicious expert.
Byrd-SAGA reduces variance to robustify SGD against Byzantine attacks.
A new algorithm RESYNC for defenders against malicious attackers in multi-player bandits.
Backdoor attacks on DRL-based traffic controllers cause stop-and-go waves or crashes.
Paper detects adversarial speech inputs with high accuracy.
RW-based learning is vulnerable to the Pac-Man attack, which eliminates active RWs.
Paper defends LSTM-based text classification models from backdoor attacks.
Paper tackles Byzantine attacks in distributed learning with a new ADMM method.
GEM detects malicious accounts using adaptive embeddings from heterogeneous graphs.
MALCOM generates fake comments to fool fake news detectors.
PRISM-FCP improves federated prediction robustness against Byzantine attacks.
Information systems have widely been the target of malware attacks. Traditional signature-based malicious program detection algorithms can only detect known malware and are prone to evasion techniques such as binary obfuscation, while behavior-based approaches highly rely on the malware training samples and incur prohi…
Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image. Adversarial examples are generated by a malicious adversary by obtaining access…
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an ind…
The rapid digital transformation without security considerations has resulted in the rise of global-scale cyberattacks. The first line of defense against these attacks are Network Intrusion Detection Systems (NIDS). Once deployed, however, these systems work as blackboxes with a high rate of false positives with no mea…
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversar…
Machine learning detects phishing websites by identifying common characteristics.
Paper proposes a new black-box adversarial attack using normalizing flows.
Paper shows how to fool mammogram classifiers with adversarial attacks.
Proposes a method to improve Byzantine-robustness in compressed federated learning.
Nowadays, organizations collect vast quantities of accounting relevant transactions, referred to as 'journal entries', in 'Enterprise Resource Planning' (ERP) systems. The aggregation of those entries ultimately defines an organization's financial statement. To detect potential misstatements and fraud, international au…
Phishing is the simplest form of cybercrime with the objective of baiting people into giving away delicate information such as individually recognizable data, banking and credit card details, or even credentials and passwords. This type of simple yet most effective cyber-attack is usually launched through emails, phone…
Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off between the data privacy and utility. We characterize the optimal data releasing …
Efficiently creates label-consistent backdoor attacks without obvious mislabeling.
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs…
As the prevalence and everyday use of machine learning algorithms, along with our reliance on these algorithms grow dramatically, so do the efforts to attack and undermine these algorithms with malicious intent, resulting in a growing interest in adversarial machine learning. A number of approaches have been developed …
New approach shows backdoor attacks are indistinguishable from natural data features.
Bullseye Polytope improves clean-label poisoning attacks in transfer learning.
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce ima…
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-le…
Adversarial attacks have always been a serious threat for any data-driven model. In this paper, we explore subspaces of adversarial examples in unitary vector domain, and we propose a novel detector for defending our models trained for environmental sound classification. We measure chordal distance between legitimate a…
New adversarial training enhances malware detectors against various attacks.
New attacks prevent both supervised and contrastive learning from private data.
Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federa…