相关论文: AI Deception: Risks, Dynamics, and Controls
The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address those risks, while eroding confidence in AI systems and the…
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…
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…
Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and problem-solving. These advancements have prompted a renewed…
Although artificial intelligence (AI) has achieved many feats at a rapid pace, there still exist open problems and fundamental shortcomings related to performance and resource efficiency. Since AI researchers benchmark a significant…
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…
The convergence of artificial intelligence (AI) and synthetic biology is rapidly accelerating the pace of biological discovery and engineering. AI techniques, such as large language models and biological design tools, are enabling the…
The ability to discern between true and false information is essential to making sound decisions. However, with the recent increase in AI-based disinformation campaigns, it has become critical to understand the influence of deceptive…
Defensive deception is a promising approach for cyber defense. Via defensive deception, the defender can anticipate attacker actions; it can mislead or lure attacker, or hide real resources. Although defensive deception is increasingly…
The significant advancements in applying Artificial Intelligence (AI) to healthcare decision-making, medical diagnosis, and other domains have simultaneously raised concerns about the fairness and bias of AI systems. This is particularly…
Artificial Intelligence (AI) systems have historically been used as tools that execute narrowly defined tasks. Yet recent advances in AI have unlocked possibilities for a new class of models that genuinely collaborate with humans in complex…
The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…
Artificial intelligence is fundamentally changing how health content is encountered and acted upon across both the information and healthcare ecosystems. AI systems now generate claims, curate information, interpret symptoms, synthesize…
When should we defer to AI outputs over human expert judgment? Drawing on recent work in social epistemology, I motivate the idea that some AI systems qualify as Artificial Epistemic Authorities (AEAs) due to their demonstrated reliability…
The discourse on risks from advanced AI systems ("AIs") typically focuses on misuse, accidents and loss of control, but the question of AIs' moral status could have negative impacts which are of comparable significance and could be realised…
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment…
The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…
Advanced Artificial Intelligence (AI) systems, specifically large language models (LLMs), have the capability to generate not just misinformation, but also deceptive explanations that can justify and propagate false information and erode…
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…
This paper examines the systemic risks posed by incremental advancements in artificial intelligence, developing the concept of `gradual disempowerment', in contrast to the abrupt takeover scenarios commonly discussed in AI safety. We…