Related papers: Plausible Deniability in Web Search -- From Detect…

Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with the growing demand for the right to be forgotten, machine…

Phishing is an increasingly sophisticated method to steal personal user information using sites that pretend to be legitimate. In this paper, we take the following steps to identify phishing URLs. First, we carefully select lexical features…

Search engines have vast technical capabilities to retain Internet search logs for each user and thus present major privacy vulnerabilities to both individuals and organizations in revealing user intent. Additionally, many of the web search…

Today's high-stakes adversarial interactions feature attackers who constantly breach the ever-improving security measures. Deception mitigates the defender's loss by misleading the attacker to make suboptimal decisions. In order to formally…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

In the growing world of the internet, the number of ways to obtain crucial data such as passwords and login credentials, as well as sensitive personal information has expanded. Page impersonation, often known as phishing, is one method of…

Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets…

Subset selection algorithms are ubiquitous in AI-driven applications, including, online recruiting portals and image search engines, so it is imperative that these tools are not discriminatory on the basis of protected attributes such as…

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,…

Smart speakers are gaining popularity. However, such devices can put the user's privacy at risk whenever hot-words are misinterpreted and voice data is recorded without the user's consent. To mitigate such risks, smart speakers provide…

This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks. First, we propose to quantitatively measure the trade-off between model accuracy and privacy losses…

Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates differently, or their writing style may indirectly reveal demographic…

Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for…

Machine learning based phishing website detectors (ML-PWD) are a critical part of today's anti-phishing solutions in operation. Unfortunately, ML-PWD are prone to adversarial evasions, evidenced by both academic studies and analyses of…

Refusal discovery is the task of identifying the full set of topics that a language model refuses to discuss. We introduce this new problem setting and develop a refusal discovery method, Iterated Prefill Crawler (IPC), that uses token…

DeepFake is becoming a real risk to society and brings potential threats to both individual privacy and political security due to the DeepFaked multimedia are realistic and convincing. However, the popular DeepFake passive detection is an…

Privacy is a well-understood concept in the physical world, with us all desiring some escape from the public gaze. However, while individuals might recognise locking doors as protecting privacy, they have difficulty practising equivalent…

Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors. As automated classifiers are increasingly used in industrial control systems and machinery, these adversarial errors could grow to be a…

In eDiscovery, a party to a lawsuit or similar action must search through available information to identify those documents and files that are relevant to the suit. Search efforts tend to identify less than 100% of the relevant documents…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…