Related papers: Can't Hide Behind the API: Stealing Black-Box Comm…

The predominance of machine learning models in many spheres of human activity has led to a growing demand for their transparency. The transparency of models makes it possible to discern some factors, such as security or non-discrimination.…

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning…

This paper addresses the gap between general-purpose text embeddings and the specific demands of item retrieval tasks. We demonstrate the shortcomings of existing models in capturing the nuances necessary for zero-shot performance on item…

Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, and more. These new benchmarks push embeddings to work for any…

When training a machine learning model, it is standard procedure for the researcher to have full knowledge of both the data and model. However, this engenders a lack of trust between data owners and data scientists. Data owners are…

Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document…

This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vulnerability of supervised machine learning models (e.g.,…

The tremendous commercial potential of large language models (LLMs) has heightened concerns about their unauthorized use. Third parties can customize LLMs through fine-tuning and offer only black-box API access, effectively concealing…

The exceptional performance of diffusion models establishes them as high-value intellectual property but exposes them to unauthorized replication. Existing protection methods either modify the model to embed watermarks, which impairs…

Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns…

Serious crime modelling typically needs to be undertaken securely behind a firewall where police knowledge and capabilities can remain undisclosed. Data informing an ongoing incident is often sparse, with a large proportion of relevant data…

Large Language Models (LLMs) are increasingly deployed in mission-critical systems, facilitating tasks such as satellite operations, command-and-control, military decision support, and cyber defense. Many of these systems are accessed…

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have…

Text data are often encoded as dense vectors, known as embeddings, which capture semantic, syntactic, contextual, and domain-specific information. These embeddings, widely adopted in various applications, inherently contain rich information…

Machine Learning-as-a-Service, a pay-as-you-go business pattern, is widely accepted by third-party users and developers. However, the open inference APIs may be utilized by malicious customers to conduct model extraction attacks, i.e.,…

Human-annotated datasets with explicit difficulty ratings are essential in intelligent educational systems. Although embedding vector spaces are widely used to represent semantic closeness and are promising for analyzing text difficulty,…