Related papers: PRISM Risk Signal Framework: Hierarchy-Based Red L…
As generative AI systems are increasingly deployed in real-world applications, regulating multiple dimensions of model behavior has become essential. We focus on test-time filtering: a lightweight mechanism for behavior control that…
Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but…
Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…
Organizations and governments that develop, deploy, use, and govern AI must coordinate on effective risk mitigation. However, the landscape of AI risk mitigation frameworks is fragmented, uses inconsistent terminology, and has gaps in…
We present a novel framework that bridges the gap between the interpretability of decision trees and the advanced reasoning capabilities of large language models (LLMs) to predict startup success. Our approach leverages chain-of-thought…
Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…
Agentic AI systems, built upon large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligence, autonomy, collaboration, and decision-making across enterprise and societal domains. This review presents a…
Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the intersection of AI safety, moral philosophy, and cognitive science. We introduce Morality Chains, a novel…
Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…
As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…
As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…
Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…
The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…
Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing approaches, represented by process reward models (PRMs),…
AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination. This paper…
Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason strategically about its circumstances, is widely considered among the most dangerous emergent…
As artificial intelligence systems evolve from passive assistants into autonomous agents capable of executing consequential actions, the security boundary shifts from model outputs to tool execution. Traditional security paradigms - log…
As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources (e.g., model developers, users, and tools) within a single prompt context.…
As Large Language Models (LLMs) transition from standalone chat interfaces to foundational reasoning layers in multi-agent systems and recursive evaluation loops (LLM-as-a-judge), the detection of durable, provider-level behavioral…
The conversation around artificial intelligence (AI) often focuses on safety, transparency, accountability, alignment, and responsibility. However, AI security (i.e., the safeguarding of data, models, and pipelines from adversarial…