相关论文: Safetywashing: Do AI Safety Benchmarks Actually Me…
The potential presented by Artificial Intelligence (AI) for healthcare has long been recognised by the technical community. More recently, this potential has been recognised by policymakers, resulting in considerable public and private…
The number and importance of AI-based systems in all domains is growing. With the pervasive use and the dependence on AI-based systems, the quality of these systems becomes essential for their practical usage. However, quality assurance for…
Digital technologies have dramatically accelerated the digital transformation in process industries, boosted new industrial applications, upgraded the production system, and enhanced operational efficiency. In contrast, the challenges and…
AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…
Building trust in AI-based systems is deemed critical for their adoption and appropriate use. Recent research has thus attempted to evaluate how various attributes of these systems affect user trust. However, limitations regarding the…
The automation of AI R&D (AIRDA) could have significant implications, but its extent and ultimate effects remain uncertain. We need empirical data to resolve these uncertainties, but existing data (primarily capability benchmarks) may not…
As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…
The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…
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…
Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This position paper argues that current implementations risk serving as symbolic…
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…
Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats…
When training powerful AI systems to perform complex tasks, it may be challenging to provide training signals which are robust to optimization. One concern is \textit{measurement tampering}, where the AI system manipulates multiple…
As AI assistants become integrated into safety engineering workflows for Physical AI systems, a critical question emerges: does AI assistance improve safety analysis quality, or introduce systematic blind spots that surface only through…
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented…
While games have been used extensively as milestones to evaluate game-playing AI, there exists no standardised framework for reporting the obtained observations. As a result, it remains difficult to draw general conclusions about the…
Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify…
Artificial intelligence (AI) is increasingly being used to augment and automate cyber operations, altering the scale, speed, and accessibility of malicious activity. These shifts raise urgent questions about when AI systems introduce…
As AI systems appear to exhibit ever-increasing capability and generality, assessing their true potential and safety becomes paramount. This paper contends that the prevalent evaluation methods for these systems are fundamentally…
More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense…