Related papers: ILION: Deterministic Pre-Execution Safety Gates fo…
Artificial intelligence pipelines -- spanning data collection, model training, deployment, and post-deployment monitoring -- concentrate ethical risks that intensify with multimodal and agentic systems. Existing governance instruments,…
When an LLM agent reads a confidential file, then writes a summary, then emails it externally, no single step is unsafe, but the sequence is a data leak. We call this safety drift: individually safe actions compounding into violations.…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…
The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts.…
Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…
The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service (DoS) risks, Automatic Exploit Generation (AEG) systems suffer from semantic blindness, and Large…
AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content…
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…
Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…
We propose a foundational runtime actuarial layer for autonomous AI agents in which every side-effect-bearing action carries a time-consistent, counterfactual risk toll computed against a contractually fixed safe default, inside an explicit…
Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…
AI agents that execute tasks via tool calls frequently hallucinate results - fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge…
Securing Agentic Artificial Intelligence (AI) systems requires addressing the complex cyber risks introduced by autonomous, decision-making, and adaptive behaviors. Agentic AI systems are increasingly deployed across industries,…
Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…
The adoption of Internet of Things (IoT) systems at the network edge of smart architectures is increasing rapidly, intensifying the need for security mechanisms that are both adaptive and resource-efficient. In such environments, runtime…
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…
Object-Goal Navigation (ObjectNav) requires an agent to autonomously explore an unknown environment and navigate toward target objects specified by a semantic label. While prior work has primarily studied zero-shot ObjectNav under 2D…
Due to the labor-intensive nature of manual test oracle construction, various automated testing techniques have been proposed to enhance the reliability of Natural Language Processing (NLP) software. In theory, these techniques mutate an…