Related papers: Crash-Consistent Checkpointing for AI Training on …
The accelerating adoption of large language models, retrieval-augmented generation pipelines, and multi-agent AI workflows has created a structural governance crisis. Organizations cannot govern what they cannot see, and existing compliance…
Iterative methods are commonly used approaches to solve large, sparse linear systems, which are fundamental operations for many modern scientific simulations. When the large-scale iterative methods are running with a large number of ranks…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…
A natural method to evaluate the effectiveness of a testing technique is to measure the defect detection rate when applying the created test cases. Here, real or artificial software defects can be injected into the source code of software.…
Increasing automation in vehicles enabled by increased connectivity to the outside world has exposed vulnerabilities in previously siloed automotive networks like controller area networks (CAN). Attributes of CAN such as broadcast-based…
This work studies the robust evaluation of iterative stochastic purification defenses under white-box adversarial attacks. Our key technical insight is that gradient checkpointing makes exact end-to-end gradient computation through long…
Deep Neural Networks (DNNs) are used in a wide variety of applications. However, as in any software application, DNN-based apps are afflicted with bugs. Previous work observed that DNN bug fix patterns are different from traditional bug fix…
An autonomous AI ecosystem (SUBSTRATE S3), generating product specifications without explicit instructions about formal methods, independently proposed the use of Z3 SMT solver across six distinct domains of AI safety: verification of…
We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five…
The amount of data generated by scientific and commercial applications is growing at an ever-increasing pace. This data is often moved between geographically distributed sites for various purposes such as collaboration and backup which has…
Network architecture search (NAS), in particular the differentiable architecture search (DARTS) method, has shown a great power to learn excellent model architectures on the specific dataset of interest. In contrast to using a fixed…
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and…
The widespread adoption of AI-assisted development tools in 2025 -- and the emergence of vibe coding, a practice of generating complete applications from natural language without verification -- exposed a critical and tool-agnostic failure…
The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
In this paper, we present a domain specific process to assist the verification of observer-based fault detection software. Observer-based fault detection systems, like control systems, yield invariant properties of quadratic types. These…
The advancement and adoption of Artificial Intelligence (AI) models across diverse domains have transformed the way we interact with technology. However, it is essential to recognize that while AI models have introduced remarkable…
Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of…
A well-known testing method for the safety evaluation and real-time validation of automotive software systems (ASSs) is Fault Injection (FI). In accordance with the ISO 26262 standard, the faults are introduced artificially for the purpose…
Frontier artificial intelligence (AI) systems present both benefits and risks to society. Safety cases - structured arguments supported by evidence - are one way to help ensure the safe development and deployment of these systems. Yet the…