Related papers: Beyond Full Poisoning: Effective Availability Atta…

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

Upcoming certification actions related to the security of machine learning (ML) based systems raise major evaluation challenges that are amplified by the large-scale deployment of models in many hardware platforms. Until recently, most of…

To leverage data and computation capabilities of mobile devices, machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models, resulting in the new paradigm of edge learning. In this paper,…

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired…

Large language models (LLMs) can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long,…

In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks…

Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard…

The performance of machine learning models depends on the quality of the underlying data. Malicious actors can attack the model by poisoning the training data. Current detectors are tied to either specific data types, models, or attacks,…

Increased interconnectivity of Cyber-Physical Systems, by design or otherwise, increases the cyber attack surface and attack vectors. Observing the effects of these attacks is helpful in detecting them. In this paper, we show that many…

Poisoning attacks have emerged as a significant security threat to machine learning algorithms. It has been demonstrated that adversaries who make small changes to the training set, such as adding specially crafted data points, can hurt the…

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…

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…

With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…

Attributing APT (Advanced Persistent Threat) malware to their respective groups is crucial for threat intelligence and cybersecurity. However, APT adversaries often conceal their identities, rendering attribution inherently adversarial.…

As deep learning models are increasingly deployed in safety-critical applications, evaluating their vulnerabilities to adversarial perturbations is essential for ensuring their reliability and trustworthiness. Over the past decade, a large…

Modern processors widely equip the Performance Monitoring Unit (PMU) to collect various architecture and microarchitecture events. Software developers often utilize the PMU to enhance program's performance, but the potential side effects…

Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model. Previous Weight regularizations (e.g., L1 regularization)…

A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset. These attacks are currently evaluated using…

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…