Related papers: Resilient Linear Classification: An Approach to De…

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

Concerns for the resilience of Cyber-Physical Systems (CPS)s in critical infrastructure are growing. CPS integrate sensing, computation, control, and networking into physical objects and mission-critical services, connecting traditional…

Cyber-physical systems (CPSs) in modern real-time applications integrate numerous control units linked through communication networks, each responsible for executing a mix of real-time safety-critical and non-critical tasks. To ensure…

Cyber-physical systems integrate computation, communication, and physical capabilities to interact with the physical world and humans. Besides failures of components, cyber-physical systems are prone to malignant attacks, and specific…

Backdoor and data-poisoning attacks can flip predictions with tiny training corruptions, yet a sharp theory linking poisoning strength, overparameterization, and regularization is lacking. We analyze ridge least squares with an unpenalized…

Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data. However, due to their reliance on the known labels to infer the unknown…

The industry increasingly relies on deep learning (DL) technology for manufacturing inspections, which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection systems derive defect patterns from labeled…

Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent…

Contemporary machine learning applications often involve classification tasks with many classes. Despite their extensive use, a precise understanding of the statistical properties and behavior of classification algorithms is still missing,…

Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to…

Advanced classification algorithms are being increasingly used in safety-critical applications like health-care, engineering, etc. In such applications, miss-classifications made by ML algorithms can result in substantial financial or…

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

Increased connectivity and remote reprogrammability/reconfigurability features of embedded devices in current-day power systems (including interconnections between information technology -- IT -- and operational technology -- OT --…

Power distribution systems (PDS) serve as the backbone of our modern society, ensuring electricity reaches homes, businesses, and critical infrastructure. However, the increasing digitization and interconnectivity of these systems have…

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…

Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance…

Cyber-physical systems come with increasingly complex architectures and failure modes, which complicates the task of obtaining accurate system reliability models. At the same time, with the emergence of the (industrial) Internet-of-Things,…