Related papers: When Human cognitive modeling meets PINs: User-ind…
Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on preference examples, prompting, and input/output filtering. Despite good results, LLMs remain…
Placing a human in the loop may abate the risks of deploying AI systems in safety-critical settings (e.g., a clinician working with a medical AI system). However, mitigating risks arising from human error and uncertainty within such…
Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data. Specifically, PPI methods provide tighter confidence intervals by combining small amounts of human-labeled data with…
Users' website browsing history contains sensitive information, like health conditions, political interests, financial situations, etc. Some recent studies have demonstrated the possibility of inferring website fingerprints based on…
The PIN/TAN-system is an authentication and authorization scheme used in e-business. Like other similar schemes it is successfully attacked by criminals. After shortly classifying the various kinds of attacks we accomplish malicious code…
The quick and pervasive infiltration of decision support systems, artificial intelligence, and data mining in consumer electronics and everyday life in general has been significant in recent years. Fields such as UX have been facilitating…
We propose that by integrating behavioural biometric gestures---such as drawing figures on a touch screen---with challenge-response based cognitive authentication schemes, we can benefit from the properties of both. On the one hand, we can…
Generating commonsense assertions within a given story context remains a difficult task for modern language models. Previous research has addressed this problem by aligning commonsense inferences with stories and training language…
Conversational recommender systems proactively query users with relevant "key terms" and leverage the feedback to elicit users' preferences for personalized recommendations. Conversational contextual bandits, a prevalent approach in this…
Wireless devices resorting to event-triggered communications have been proved to suffer critical privacy issues, due to the intrinsic leakage associated with radio-frequency (RF) emissions. In this paper, we move the attack frontier forward…
The purpose of research: Detection of cybersecurity incidents and analysis of decision support and assessment of the effectiveness of measures to counter information security threats based on modern generative models. The methods of…
In recent decades, criminals have increasingly used the web to research, assist and perpetrate criminal behaviour. One of the most important ways in which law enforcement can battle this growing trend is through accessing pertinent…
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…
Graph knowledge models and ontologies are very powerful modeling and re asoning tools. We propose an effective approach to model network attacks and attack prediction which plays important roles in security management. The goals of this…
Among user authentication methods, behavioural biometrics has proven to be effective against identity theft as well as user-friendly and unobtrusive. One of the most popular traits in the literature is keystroke dynamics due to the large…
We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attacks. We find that across a variety of attacks, increased…
Many security protocols rely on the assumptions on the physical properties in which its protocol sessions will be carried out. For instance, Distance Bounding Protocols take into account the round trip time of messages and the transmission…
Building meaningful interoperation with external software units requires performing the conceptual interoperability analysis that starts with identifying the conceptual interoperability constraints of each software unit, then it compares…
Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…
Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically…