Related papers: ASTRA: Autonomous Spatial-Temporal Red-teaming for…
Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing,…
ASTRA is a Python package that provides a modular, instrument-independent interface for working with high-resolution stellar spectra. Designed to support data from multiple spectrographs, including ESPRESSO (Pepe et al., 2021), HARPS (Mayor…
Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method…
The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a…
Autonomous vehicles (AVs) have demonstrated significant potential in revolutionizing transportation, yet ensuring their safety and reliability remains a critical challenge, especially when exposed to dynamic and unpredictable environments.…
Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the…
Practitioners have reported a directional pattern in AI-assisted code generation: AI-generated code tends to fail quietly, preserving the appearance of functionality while degrading or concealing guarantees. This paper introduces the…
This paper introduces ASTRA, a novel method for improving Automatic Speech Recognition (ASR) through text injection.Unlike prevailing techniques, ASTRA eliminates the need for sampling to match sequence lengths between speech and text…
API misuse introduces security vulnerabilities, system failures, and increases maintenance costs, all of which remain critical challenges in software development. Existing detection approaches rely on static analysis or machine…
Extensive simulation-based testing is important for assuring the safety of autonomous driving systems (ADS). However, generating safety-critical traffic scenarios remains challenging because failures often arise from rare, complex…
Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…
While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on human-specified workflows. This dependence on manually designed workflows suffers from human biases…
Large Language Models (LLMs) have recently gained attention due to their ability to understand and generate sophisticated human-like content. However, ensuring their safety is paramount as they might provide harmful and unsafe responses.…
With the rise of increasingly complex autonomous systems powered by black box AI models, there is a growing need for Run Time Assurance (RTA) systems that provide online safety filtering to untrusted primary controller output. Currently,…
Multi-device inference can reduce Transformer latency by parallelizing computation. However, existing methods require high inter-device bandwidth, making them impractical for bandwidth-constrained environments. We present ASTRA, a…
Software safety is a crucial aspect during the development of modern safety-critical systems. Software is becoming responsible for most of the critical functions of systems. Therefore, the software components in the systems need to be…
Nowadays, web services play a major role in the development of enterprise applications. Many such applications are now developed using a service-oriented architecture (SOA), where microservices is one of its most popular kind. A RESTful web…
We present ASTRA (A} Scene-aware TRAnsformer-based model for trajectory prediction), a light-weight pedestrian trajectory forecasting model that integrates the scene context, spatial dynamics, social inter-agent interactions and temporal…
This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions: it enhances steerability by generating parameterised…
The state transition algorithm (STA), as an intelligent optimization method grounded in constructivist learning, has been demonstrated to be highly effective in solving complex optimization problems. However, the standard STA suffers from…