Search Results for author:
Found 17 papers, 4 papers with code
On the Robustness of Malware Detectors to Adversarial Samples
They have been demonstrated to pose significant challenges in domains like image classification, with results showing that an adversarially perturbed image to evade detection against one classifier is most likely transferable to other classifiers.
ConvoCache: Smart Re-Use of Chatbot Responses
We present ConvoCache, a conversational caching system that solves the problem of slow and expensive generative AI models in spoken chatbots.
SPGNN-API: A Transferable Graph Neural Network for Attack Paths Identification and Autonomous Mitigation
Attack paths are the potential chain of malicious activities an attacker performs to compromise network assets and acquire privileges through exploiting network vulnerabilities.
Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories
We generate 150 examples of misinformation, of which 114 (76%) were remembered by BlenderBot 2 when combined with a personal statement.
Privacy-Preserving Record Linkage for Cardinality Counting
Several applications require counting the number of distinct items in the data, which is known as the cardinality counting problem.
A Differentially Private Framework for Deep Learning with Convexified Loss Functions
Under a black-box setting, based on this global sensitivity, to control the overall noise injection, we propose a novel output perturbation framework by injecting DP noise into a randomly sampled neuron (via the exponential mechanism) at the output layer of a baseline non-private neural network trained with a convexified loss function.
On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models
In this paper, we take a closer look at another inference attack reported in literature, called attribute inference, whereby an attacker tries to infer missing attributes of a partially known record used in the training dataset by accessing the machine learning model as an API.
Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning
In this work, we empirically evaluate various implementations of differential privacy (DP), and measure their ability to fend off real-world privacy attacks, in addition to measuring their core goal of providing accurate classifications.
Cryptography and Security
The Cost of Privacy in Asynchronous Differentially-Private Machine Learning
The experiments illustrate that collaboration among more than 10 data owners with at least 10, 000 records with privacy budgets greater than or equal to 1 results in a superior machine-learning model in comparison to a model trained in isolation on only one of the datasets, illustrating the value of collaboration and the cost of the privacy.
Modelling and Quantifying Membership Information Leakage in Machine Learning
We use conditional mutual information leakage to measure the amount of information leakage from the trained machine learning model about the presence of an individual in the training dataset.
On the Resilience of Biometric Authentication Systems against Random Inputs
The average false positive rate (FPR) of the system, i. e., the rate at which an impostor is incorrectly accepted as the legitimate user, may be interpreted as a measure of the success probability of such an attack.
On Inferring Training Data Attributes in Machine Learning Models
A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models.
The Value of Collaboration in Convex Machine Learning with Differential Privacy
In this paper, we apply machine learning to distributed private data owned by multiple data owners, entities with access to non-overlapping training datasets.
DaDiDroid: An Obfuscation Resilient Tool for Detecting Android Malware via Weighted Directed Call Graph Modelling
We examine the graph features of mobile apps code by building weighted directed graphs of the API calls, and verify that malicious apps often share structural similarities that can be used to differentiate them from benign apps, even under a heavily "polluted" training set where a large majority of the apps are obfuscated.
Cryptography and Security
Not All Attributes are Created Equal: $d_{\mathcal{X}}$-Private Mechanisms for Linear Queries
However, it provides the same level of protection for all elements (individuals and attributes) in the data.
Graph Based Recommendations: From Data Representation to Feature Extraction and Application
The proposed approach is domain-independent (demonstrated on data from movies, music, and business recommender systems), and is evaluated using several state-of-the-art machine learning methods, on different recommendation tasks, and using different evaluation metrics.
Paying for Likes? Understanding Facebook Like Fraud Using Honeypots
Facebook pages offer an easy way to reach out to a very large audience as they can easily be promoted using Facebook's advertising platform.
Social and Information Networks Cryptography and Security Physics and Society
