Related papers: User Friendly Line CAPTCHAs
In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…
Chatbots have the risk of generating offensive utterances, which must be avoided. Post-deployment, one way for a chatbot to continuously improve is to source utterance/label pairs from feedback by live users. However, among users are…
Malicious bots make up about a quarter of all traffic on the web, and degrade the performance of personalization and recommendation algorithms that operate on e-commerce sites. Positive-Unlabeled learning (PU learning) provides the ability…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
Interactive technologies are getting closer to our bodies and permeate the infrastructure of our homes. While such technologies offer many benefits, they can also cause an initial feeling of unease in users. It is important for…
The Turing Test (TT) checks for human intelligence, rather than any putative general intelligence. It involves repeated interaction requiring learning in the form of adaption to the human conversation partner. It is a macro-level post-hoc…
With the rise of prolific ChatGPT, the risk and consequences of AI-generated text has increased alarmingly. To address the inevitable question of ownership attribution for AI-generated artifacts, the US Copyright Office released a statement…
The human face is one of the most crucial parts in interhuman communication. Even when parts of the face are hidden or obstructed the underlying facial movements can be understood. Machine learning approaches often fail in that regard due…
The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations. The traditional setting limits each participant to one message at a time and requires constant human participation. This fails to reflect a…
Technologies increasingly mimic human-like social behaviours. Beyond prototypical conversational agents like chatbots, this also applies to basic automated systems like app notifications or self-checkout machines that address or 'talk to'…
With the help of online tools, unscrupulous authors can today generate a pseudo-scientific article and attempt to publish it. Some of these tools work by replacing or paraphrasing existing texts to produce new content, but they have a…
The significant progress in the development of Large Language Models has contributed to blurring the distinction between human and AI-generated text. The increasing pervasiveness of AI-generated text and the difficulty in detecting it poses…
The recent advancement in technology breaks the barriers to communication between users and computers. The communication between humans and computers includes emotion and gesture recognition. Emotions can be recognized on the face of humans…
CAPTCHAs are designed to prevent malicious bot programs from abusing websites. Most online service providers deploy audio CAPTCHAs as an alternative to text and image CAPTCHAs for visually impaired users. However, prior research…
Background: Testing and validation of the semantic correctness of patches provided by tools for Automated Program Repairs (APR) has received a lot of attention. Yet, the eventual acceptance or rejection of suggested patches for real world…
In spite of the successful application in many fields, machine learning models today suffer from notorious problems like vulnerability to adversarial examples. Beyond falling into the cat-and-mouse game between adversarial attack and…
Audio CAPTCHAs are supposed to provide a strong defense for online resources; however, advances in speech-to-text mechanisms have rendered these defenses ineffective. Audio CAPTCHAs cannot simply be abandoned, as they are specifically named…
As LLM-based computer-use agents (CUAs) begin to autonomously interact with real-world interfaces, understanding their vulnerability to manipulative interface designs becomes increasingly critical. We introduce SusBench, an online benchmark…
This paper assumes the hypothesis that human learning is perception based, and consequently, the learning process and perceptions should not be represented and investigated independently or modeled in different simulation spaces. In order…
ChatGPT has the ability to generate grammatically flawless and seemingly-human replies to different types of questions from various domains. The number of its users and of its applications is growing at an unprecedented rate. Unfortunately,…