Related papers: SnatchML: Hijacking ML models without Training Acc…

Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…

Security attacks are hard to understand, often expressed with unfriendly and limited details, making it difficult for security experts and for security analysts to create intelligible security specifications. For instance, to explain Why…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the…

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, the inductive GNNs,…

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity structures that enable…

Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and specialized expertise have historically restricted their wide…

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…

Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model…

Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model.…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…

Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML) models are expensive to train, in part because data is hard…

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive---new systems and models are being deployed in every…

Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds…

Cyber attacks constitute a significant threat to organizations with implications ranging from economic, reputational, and legal consequences. As cybercriminals' techniques get sophisticated, information security professionals face a more…

We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the…

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model,…

Triggerable watermarking enables model owners to assert ownership against model extraction attacks. However, most existing approaches require additional training, which limits post-deployment flexibility, and the lack of clear theoretical…

Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during…