Related papers: Difficulties with Evaluating a Deception Detector …
Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to…
Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception…
Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a…
The rapid development of autoregressive Large Language Models (LLMs) has significantly improved the quality of generated texts, necessitating reliable machine-generated text detectors. A huge number of detectors and collections with AI…
Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many…
The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…
Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…
AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…
The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present…
Powerful predictive AI systems have demonstrated great potential in augmenting human decision making. Recent empirical work has argued that the vision for optimal human-AI collaboration requires 'appropriate reliance' of humans on AI…
Humans and machines interact more frequently than ever and our societies are becoming increasingly hybrid. A consequence of this hybridisation is the degradation of societal trust due to the prevalence of AI-enabled deception. Yet, despite…
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure…
Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning is a field of AI that enables systems to…
In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of…
This position paper argues for two claims regarding AI testing and evaluation. First, to remain informative about deployment behaviour, evaluations need account for the possibility that AI systems understand their circumstances and reason…
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…
International agreements about AI development may be required to reduce catastrophic risks from advanced AI systems. However, agreements about such a high-stakes technology must be backed by verification mechanisms--processes or tools that…
Artificial intelligence (AI) systems have become increasingly popular in many areas. Nevertheless, AI technologies are still in their developing stages, and many issues need to be addressed. Among those, the reliability of AI systems needs…
The community deception problem is about how to hide a target community C from community detection algorithms. The need for deception emerges whenever a group of entities (e.g., activists, police enforcements) want to cooperate while…
This paper presents a critical analysis of generative Artificial Intelligence (AI) detection tools in higher education assessments. The rapid advancement and widespread adoption of generative AI, particularly in education, necessitates a…