Related papers: Towards Unifying Quantitative Security Benchmarkin…
The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…
In the vast domain of cybersecurity, the transition from reactive defense to offensive has become critical in protecting digital infrastructures. This paper explores the integration of Artificial Intelligence (AI) into offensive…
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…
The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…
In the artificial intelligence space, as we transition from isolated large language models to autonomous agents capable of complex reasoning and tool use. While foundational architectures and local context management protocols have been…
Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to evaluate agents on complex, real-world tasks. These…
Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…
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…
This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…
Traditional static cybersecurity models often struggle with scalability, real-time detection, and contextual responsiveness in the current digital product ecosystems which include cloud services, application programming interfaces (APIs),…
Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a…
Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations,…
Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…
The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…
Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex…
This study presents a structured approach to evaluating vulnerabilities within quantum cryptographic protocols, focusing on the BB84 quantum key distribution method and National Institute of Standards and Technology (NIST) approved…
Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to…