Related papers: Crash-Consistent Checkpointing for AI Training on …
Multi-Sensor Fusion (MSF) based perception systems have been the foundation in supporting many industrial applications and domains, such as self-driving cars, robotic arms, and unmanned aerial vehicles. Over the past few years, the fast…
Recently, advances in deep learning have been observed in various fields, including computer vision, natural language processing, and cybersecurity. Machine learning (ML) has demonstrated its ability as a potential tool for anomaly…
Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). However, such components may introduce new types of hazards that can have disastrous consequences and need to be addressed for…
AI Assurance -- producing the machine-readable evidence required to demonstrate compliance with AI governance frameworks -- has mature policy scaffolding but lacks the infrastructure to operationalize it. Organizations building high-risk AI…
In-Memory Computing (IMC) introduces a new paradigm of computation that offers high efficiency in terms of latency and power consumption for AI accelerators. However, the non-idealities and defects of emerging technologies used in advanced…
The increasing complexity of software systems and the sophistication of cyber-attacks have underscored the need for reliable automated software vulnerability detection. Data-driven approaches using deep learning models show promise but…
Adversarial examples pose a security risk as they can alter decisions of a machine learning classifier through slight input perturbations. Certified robustness has been proposed as a mitigation where given an input $\mathbf{x}$, a…
Transient or permanent faults in hardware can render the output of Neural Networks (NN) incorrect without user-specific traces of the error, i.e. silent data errors (SDE). On the other hand, modern NNs also possess an inherent redundancy…
Autonomous systems must sustain justified confidence in their correctness and safety across their operational lifecycle-from design and deployment through post-deployment evolution. Traditional assurance methods often separate…
The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…
Serverless computing has grown in popularity in recent years, with an increasing number of applications being built on Functions-as-a-Service (FaaS) platforms. By default, FaaS platforms support retry-based fault tolerance, but this is…
As AI systems integrate into critical infrastructure, security gaps in AI compliance frameworks demand urgent attention. This paper audits and quantifies security risks in three major AI governance standards: NIST AI RMF 1.0, UK's AI and…
Fault injection attacks represent a class of threats that can compromise embedded systems across multiple layers of abstraction, such as system software, instruction set architecture (ISA), microarchitecture, and physical implementation.…
Instruction tuned reasoning models are increasingly deployed with safety classifiers trained on frozen embeddings, assuming representation stability across model updates. We systematically investigate this assumption and find it fails:…
Lightweight cryptographic primitives are widely deployed in resource-constrained environments, particularly in Internet of Things (IoT) devices. Due to their public accessibility, these devices are vulnerable to physical attacks, especially…
Regulated AI workflows (such as clinical trials, medical decision support, and financial compliance) must satisfy strict auditability and integrity requirements. Existing audit-trail mechanisms rely on variable-length records, bulky…
Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance. To alleviate this problem, we present an efficient robust algorithm…
In recent years, machine learning (ML) based software systems are increasingly deployed in several critical applications, yet systematic testing of their behavior remains challenging due to complex model architectures, large input spaces,…
We investigate the role of artificial intelligence in cybersecurity by evaluating how machine learning techniques can detect malicious network activity and identify potential information leakage in cryptographic implementations. We conduct…
We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…