相关论文: PRISM Risk Signal Framework: Hierarchy-Based Red L…

Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first…

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle…

Ransomware continues to evolve as one of the most disruptive cyber threats, with recent variants increasingly leveraging automated and AI-assisted techniques to evade traditional signature-based defenses. Early detection of such attacks…

Reinforcement learning (RL) is increasingly used to personalize instruction in intelligent tutoring systems, yet the field lacks a formal framework for defining and evaluating pedagogical safety. We introduce a four-layer model of…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Three generations of software have transformed the role of artificial intelligence in society. In the first, programmers wrote explicit logic; in the second, neural networks learned programs from data; in the third, large language models…

Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation. Existing transparency mechanisms - including Model Cards, Datasheets,…

The deployment of AI systems faces three critical governance challenges that current frameworks fail to adequately address. First, organizations struggle with inadequate risk assessment at the use case level, exemplified by the Humana class…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Many decision-making scenarios in modern life benefit from the decision support of artificial intelligence algorithms, which focus on a data-driven philosophy and automated programs or systems. However, crucial decision issues related to…

All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk…

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning…

The $\textit{LLM-as-a-judge}$ paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: that judges evaluate text strictly on its semantic content, impervious to surrounding…

The evaluation and improvement of medical large language models (LLMs) are critical for their real-world deployment, particularly in ensuring accuracy, safety, and ethical alignment. Existing frameworks inadequately dissect domain-specific…

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar…

Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general domains such as mathematics, failing to address medical reasoning -- which is uniquely…

This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted between 2019 and early 2026 require reviewable evidence of…