Related papers: Typer vs. CAPTCHA: Private information based CAPTC…
Searching for concepts in science and technology is often a difficult task. To facilitate concept search, different types of human-generated metadata have been created to define the content of scientific and technical disclosures.…
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…
As automation bot technology and Artificial Intelligence is evolving rapidly, conventional human verification techniques like voice CAPTCHAs and knowledge-based authentication are becoming less effective. Bots and scrapers with Artificial…
CAPTCHAs remain a critical defense against automated abuse, yet modern systems suffer from well-known limitations in usability, accessibility, and resistance to increasingly capable bots and low-cost CAPTCHA farms. Behavioral and…
Even though passwords are the most convenient means of authentication, they bring along themselves the threat of dictionary attacks. Dictionary attacks may be of two kinds: online and offline. While offline dictionary attacks are possible…
The last years of the 20 th century and the beginning of the 21 th mark the facilitation trend of our real life due to the big development and progress of the computers and other intelligent devices. Algorithms based on artificial…
Privacy computing involves the extensive exchange and processing of encrypted data. For the parties involved in these interactions, how to determine the consistency of exchanged data without accessing the original data, ensuring tamper…
Recent proposals advocate using keystroke timing signals, specifically the coefficient of variation ($\delta$) of inter-keystroke intervals, to distinguish human-composed text from AI-generated content. We demonstrate that this class of…
For humans and computers, the first step in answering an open-domain question is retrieving a set of relevant documents from a large corpus. However, the strategies that computers use fundamentally differ from those of humans. To better…
Over the last decade there have been great strides made in developing techniques to compute functions privately. In particular, Differential Privacy gives strong promises about conclusions that can be drawn about an individual. In contrast,…
Deep learning technology has made it possible to generate realistic content of specific individuals. These `deepfakes' can now be generated in real-time which enables attackers to impersonate people over audio and video calls. Moreover,…
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…
Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation,…
Crowdsourcing employs human workers to solve computer-hard problems, such as data cleaning, entity resolution, and sentiment analysis. When crowdsourcing tabular data, e.g., the attribute values of an entity set, a worker's answers on the…
In recent years, crowdsourcing, aka human aided computation has emerged as an effective platform for solving problems that are considered complex for machines alone. Using human is time-consuming and costly due to monetary compensations.…
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more…
Modern computing systems inherently trust human input devices, creating an exploitable attack surface for adversarial automation. USB Human Interface Device (HID) emulation attacks, such as those enabled by the USB Rubber Ducky, exploit…
Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate…
Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thousand photos every minute. Content moderators constantly…
In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. Attack detection models can be leveraged to provide an additional check for NLP models and…