Abstract:Individuals have been increasingly interacting with online Large Language Models (LLMs), both in their work and personal lives. These interactions raise privacy issues as the LLMs are typically hosted by third-parties who can gather a variety of sensitive information about users and their companies. Text Sanitization techniques have been proposed in the literature and can be used to sanitize user prompts before sending them to the LLM. However, sanitization has an impact on the downstream task performed by the LLM, and often to such an extent that it leads to unacceptable results for the user. This is not just a minor annoyance, with clear monetary consequences as LLM services charge on a per use basis as well as great amount of computing resources wasted. We propose an architecture leveraging a Small Language Model (SLM) at the user-side to help estimate the impact of sanitization on a prompt before it is sent to the LLM, thus preventing resource losses. Our evaluation of this architecture revealed a significant problem with text sanitization based on Differential Privacy, on which we want to draw the attention of the community for further investigation.
Abstract:Two parties wish to collaborate on their datasets. However, before they reveal their datasets to each other, the parties want to have the guarantee that the collaboration would be fruitful. We look at this problem from the point of view of machine learning, where one party is promised an improvement on its prediction model by incorporating data from the other party. The parties would only wish to collaborate further if the updated model shows an improvement in accuracy. Before this is ascertained, the two parties would not want to disclose their models and datasets. In this work, we construct an interactive protocol for this problem based on the fully homomorphic encryption scheme over the Torus (TFHE) and label differential privacy, where the underlying machine learning model is a neural network. Label differential privacy is used to ensure that computations are not done entirely in the encrypted domain, which is a significant bottleneck for neural network training according to the current state-of-the-art FHE implementations. We prove the security of our scheme in the universal composability framework assuming honest-but-curious parties, but where one party may not have any expertise in labelling its initial dataset. Experiments show that we can obtain the output, i.e., the accuracy of the updated model, with time many orders of magnitude faster than a protocol using entirely FHE operations.
Abstract:Biometric authentication service providers often claim that it is not possible to reverse-engineer a user's raw biometric sample, such as a fingerprint or a face image, from its mathematical (feature-space) representation. In this paper, we investigate this claim on the specific example of deep neural network (DNN) embeddings. Inversion of DNN embeddings has been investigated for explaining deep image representations or synthesizing normalized images. Existing studies leverage full access to all layers of the original model, as well as all possible information on the original dataset. For the biometric authentication use case, we need to investigate this under adversarial settings where an attacker has access to a feature-space representation but no direct access to the exact original dataset nor the original learned model. Instead, we assume varying degree of attacker's background knowledge about the distribution of the dataset as well as the original learned model (architecture and training process). In these cases, we show that the attacker can exploit off-the-shelf DNN models and public datasets, to mimic the behaviour of the original learned model to varying degrees of success, based only on the obtained representation and attacker's prior knowledge. We propose a two-pronged attack that first infers the original DNN by exploiting the model footprint on the embedding, and then reconstructs the raw data by using the inferred model. We show the practicality of the attack on popular DNNs trained for two prominent biometric modalities, face and fingerprint recognition. The attack can effectively infer the original recognition model (mean accuracy 83\% for faces, 86\% for fingerprints), and can craft effective biometric reconstructions that are successfully authenticated with 1-vs-1 authentication accuracy of up to 92\% for some models.
Abstract:Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient. However, such systems are also at constant risk of being attacked. While the majority of attacks targeting AI-based applications aim to manipulate classifiers or training data and alter the output of an AI model, recently proposed Sponge Attacks against AI models aim to impede the classifier's execution by consuming substantial resources. In this work, we propose \textit{Dual Denial of Decision (DDoD) attacks against collaborative Human-AI teams}. We discuss how such attacks aim to deplete \textit{both computational and human} resources, and significantly impair decision-making capabilities. We describe DDoD on human and computational resources and present potential risk scenarios in a series of exemplary domains.
Abstract:Named entity recognition models (NER), are widely used for identifying named entities (e.g., individuals, locations, and other information) in text documents. Machine learning based NER models are increasingly being applied in privacy-sensitive applications that need automatic and scalable identification of sensitive information to redact text for data sharing. In this paper, we study the setting when NER models are available as a black-box service for identifying sensitive information in user documents and show that these models are vulnerable to membership inference on their training datasets. With updated pre-trained NER models from spaCy, we demonstrate two distinct membership attacks on these models. Our first attack capitalizes on unintended memorization in the NER's underlying neural network, a phenomenon NNs are known to be vulnerable to. Our second attack leverages a timing side-channel to target NER models that maintain vocabularies constructed from the training data. We show that different functional paths of words within the training dataset in contrast to words not previously seen have measurable differences in execution time. Revealing membership status of training samples has clear privacy implications, e.g., in text redaction, sensitive words or phrases to be found and removed, are at risk of being detected in the training dataset. Our experimental evaluation includes the redaction of both password and health data, presenting both security risks and privacy/regulatory issues. This is exacerbated by results that show memorization with only a single phrase. We achieved 70% AUC in our first attack on a text redaction use-case. We also show overwhelming success in the timing attack with 99.23% AUC. Finally we discuss potential mitigation approaches to realize the safe use of NER models in light of the privacy and security implications of membership inference attacks.
Abstract:Machine Learning (ML) techniques are used by most data-driven organisations to extract insights. Machine-learning-as-a-service (MLaaS), where models are trained on potentially sensitive user data and then queried by external parties are becoming a reality. However, recently, these systems have been shown to be vulnerable to Membership Inference Attacks (MIA), where a target's data can be inferred to belong or not to the training data. While the key factors for the success of MIA have not been fully understood, existing defence mechanisms only consider the model-specific properties. We investigate the impact of both the data and ML model properties on the vulnerability of ML techniques to MIA. Our analysis indicates a strong relationship between the MIA success and the properties of the data in use, such as the data size and balance between the classes as well as the model properties including the fairness in prediction and the mutual information between the records and the model's parameters. We then propose new approaches to protect ML models from MIA by using several properties, e.g. the model's fairness and mutual information between the records and the model's parameters as regularizers, which reduces the attack accuracy by 25%, while yielding a fairer and a better performing ML model.
Abstract:Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, and only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this paper, we design an optimization framework to create covert and scattered triggers for backdoor attacks, \textit{invisible backdoors}, where triggers can amplify the specific neuron activation, while being invisible to both backdoor detection methods and human inspection. We use the Perceptual Adversarial Similarity Score (PASS)~\cite{rozsa2016adversarial} to define invisibility for human users and apply $L_2$ and $L_0$ regularization into the optimization process to hide the trigger within the input data. We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as three datasets CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates and invisibility scores.
Abstract:The monitoring of large dynamic networks is a major chal- lenge for a wide range of application. The complexity stems from properties of the underlying graphs, in which slight local changes can lead to sizable variations of global prop- erties, e.g., under certain conditions, a single link cut that may be overlooked during monitoring can result in splitting the graph into two disconnected components. Moreover, it is often difficult to determine whether a change will propagate globally or remain local. Traditional graph theory measure such as the centrality or the assortativity of the graph are not satisfying to characterize global properties of the graph. In this paper, we tackle the problem of real-time monitoring of dynamic large scale graphs by developing a geometric approach that leverages notions of geometric curvature and recent development in graph embeddings using Ollivier-Ricci curvature [47]. We illustrate the use of our method by consid- ering the practical case of monitoring dynamic variations of global Internet using topology changes information provided by combining several BGP feeds. In particular, we use our method to detect major events and changes via the geometry of the embedding of the graph.