Related papers: Randomized Controlled Trials for Phishing Triage A…
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…
AI-agents help developers in different coding tasks, such as developing new features, fixing bugs, and reviewing code. Developers can write a Github issue and assign it to an AI-agent like Copilot for implementation. Based on the issue and…
Spam messes up users inbox, consumes resources and spread attacks like DDoS, MiM, phishing etc. Phishing is a byproduct of email and causes financial loss to users and loss of reputation to financial institutions. In this paper we examine…
Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming analysts with logs requiring rapidly evolving expertise. Conventional machine-learning detectors…
We propose a general approach to quantitatively assessing the risk and vulnerability of artificial intelligence (AI) systems to biased decisions. The guiding principle of the proposed approach is that any AI algorithm must outperform a…
Recent advances in artificial intelligence (AI) have shown promise in automating key aspects of Agile project management, yet their impact on team cognition remains underexplored. In this work, we investigate cognitive offloading in Agile…
In online algorithm selection (OAS), instances of an algorithmic problem class are presented to an agent one after another, and the agent has to quickly select a presumably best algorithm from a fixed set of candidate algorithms. For…
Large Language Models demonstrate remarkable capabilities yet remain fundamentally probabilistic, presenting critical reliability challenges for enterprise deployment. We introduce the Six Sigma Agent, a novel architecture that achieves…
Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension:…
We examined the mechanisms underlying productivity and performance gains from AI agents using a large-scale experiment on Pairit, a platform we developed to study human-AI collaboration. We randomly assigned 2,234 participants to…
This study introduces an innovative approach to automating Cyber Threat Intelligence (CTI) processes in industrial environments by leveraging Microsoft's AI-powered security technologies. Historically, CTI has heavily relied on manual…
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…
Despite the growing prevalence of human-AI decision making, the human-AI team's decision performance often remains suboptimal, partially due to insufficient examination of humans' own reasoning. In this paper, we explore designing AI…
Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges…
Artificial intelligence (AI)-based decision support systems hold promise for enhancing diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration can introduce and amplify cognitive biases, such as…
Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment expectations and post-deployment outcomes. We review controlled…
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this…
Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…
AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing. With studies showing that up to 40% of AI-generated code…
Phishing is a major cyber threat to organizations that can cause financial and reputational damage, threatening their existence. The technical measures against phishing should be complemented by awareness training for employees. However,…