Related papers: Evasive Intelligence: Lessons from Malware Analysi…
AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control. Agents may skip required tool calls, invoke tools unnecessarily, or…
Artificial Intelligence techniques have evolved rapidly in recent years, revolutionising the approaches used to fight against cybercriminals. But as the cyber security field has progressed, so has malware development, making it an economic…
Artificial Intelligence (AI) has become an important part of our everyday lives, yet user requirements for designing AI-assisted systems in law enforcement remain unclear. To address this gap, we conducted qualitative research on…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…
Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. These errors do not thwart agents based on state-of-the-art models. They helpfully…
Artificial Intelligence (AI) has revolutionized software development, particularly by automating repetitive tasks and improving developer productivity. While these advancements are well-documented, the use of AI-powered tools for Software…
The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic,…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…
The widespread adoption of smartphones dramatically increases the risk of attacks and the spread of mobile malware, especially on the Android platform. Machine learning-based solutions have been already used as a tool to supersede…
Growth of software size, lack of resources to perform regression testing, and failure to detect bugs faster have seen increased reliance on continuous integration and test automation. Even with greater hardware and software resources…
Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention…
Artificial Intelligence (AI) is one of the most transformative technologies of the 21st century. The extent and scope of future AI capabilities remain a key uncertainty, with widespread disagreement on timelines and potential impacts. As…
In this work we present a formal theoretical framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. Our results apply to general multi-class classifiers that map from an…
Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an…
This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…
Autonomous agents acting in the real-world often operate based on models that ignore certain aspects of the environment. The incompleteness of any given model -- handcrafted or machine acquired -- is inevitable due to practical limitations…
Artificial Intelligence (AI) Safety Institutes and governments worldwide are deciding whether they evaluate advanced AI themselves, support a private evaluation ecosystem or do both. Evaluation regimes have been established in a wide range…
As AI becomes increasingly embedded in digital games, players' attitudes de-pend not only on whether AI is used, but also on where and how it intervenes in gameplay. This study examines players' evaluative patterns toward eight AI…
There is a growing focus on how to design safe artificial intelligent (AI) agents. As systems become more complex, poorly specified goals or control mechanisms may cause AI agents to engage in unwanted and harmful outcomes. Thus it is…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…