Related papers: Stress-Testing Alignment Audits With Prompt-Level …

We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation,…

As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by…

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about…

Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses…

Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which a model appears aligned while covertly pursuing misaligned…

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…

Recent work has proposed automated red-teaming methods for testing the vulnerabilities of a given target large language model (LLM). These methods use red-teaming LLMs to uncover inputs that induce harmful behavior in a target LLM. In this…

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…

We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and…

Activation probes are attractive monitors for AI systems due to low cost and latency, but their real-world robustness remains underexplored. We ask: What failure modes arise under realistic, black-box adversarial pressure, and how can we…

Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities…

Multi-agent deployments of large language models (LLMs) are increasingly embedded in market, allocation, and governance workflows, yet covert coordination among agents can silently erode trust and social welfare. Existing audits are…

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

In the aftermath of the financial crisis, supervisory authorities have considerably altered the mode of operation of financial stress testing. Despite these efforts, significant concerns and extensive criticism have been raised by market…

Ensuring the safety and reliability of large language models (LLMs) in clinical practice is critical to prevent patient harm. However, LLMs are advancing so rapidly that static benchmarks quickly become obsolete or prone to overfitting,…

Red-teaming is a core part of the infrastructure that ensures that AI models do not produce harmful content. Unlike past technologies, the black box nature of generative AI systems necessitates a uniquely interactional mode of testing, one…

The safety and alignment of Large Language Models (LLMs) are critical for their responsible deployment. Current evaluation methods predominantly focus on identifying and preventing overtly harmful outputs. However, they often fail to…