Related papers: Visual Spoofing in content based spam detection
The CLIP network measures the similarity between natural text and images; in this work, we investigate the entanglement of the representation of word images and natural images in its image encoder. First, we find that the image encoder has…
This paper considers the problem of helping humans exercise scalable oversight over deep neural networks (DNNs). Adversarial examples can be useful by helping to reveal weaknesses in DNNs, but they can be difficult to interpret or draw…
Typographic attacks exploit the interplay between text and visual content in multimodal foundation models, causing misclassifications when misleading text is embedded within images. Existing datasets are limited in size and diversity,…
Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…
Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (ground truth) labeled spam examples, and used for classifier…
With the rapid development of machine learning for image classification, researchers have found new applications of visualization techniques in malware detection. By converting binary code into images, researchers have shown satisfactory…
User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written…
Phishing websites are still a major threat in today's Internet ecosystem. Despite numerous previous efforts, similarity-based detection methods do not offer sufficient protection for the trusted websites - in particular against unseen…
This paper introduces the problem of automatic font pairing. Font pairing is an important design task that is difficult for novices. Given a font selection for one part of a document (e.g., header), our goal is to recommend a font to be…
Machine-learning techniques are widely used in security-related applications, like spam and malware detection. However, in such settings, they have been shown to be vulnerable to adversarial attacks, including the deliberate manipulation of…
In this paper we discuss the techniques involved in the design of the famous statistical spam filters that include Naive Bayes, Term Frequency-Inverse Document Frequency, K-Nearest Neighbor, Support Vector Machine, and Bayes Additive…
Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP,…
We provide an automated graph theoretic method for identifying individual users' trusted networks of friends in cyberspace. We routinely use our social networks to judge the trustworthiness of outsiders, i.e., to decide where to buy our…
Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being…
The emergence of online services in our daily lives has been accompanied by a range of malicious attempts to trick individuals into performing undesired actions, often to the benefit of the adversary. The most popular medium of these…
In order to prevent detection and evade signature-based scanning methods, which are normally exploited by antivirus software, metamorphic viruses use several various obfuscation approaches. They transform their code in new instances as look…
In this paper, we revisit the much studied problem of Pattern Matching with Swaps (Swap Matching problem, for short). We first present a graph-theoretic model, which opens a new and so far unexplored avenue to solve the problem. Then, using…
The arm race between spambots and spambot-detectors is made of several cycles (or generations): a new wave of spambots is created (and new spam is spread), new spambot filters are derived and old spambots mutate (or evolve) to new species.…
E-commerce is the fastest-growing segment of the economy. Online reviews play a crucial role in helping consumers evaluate and compare products and services. As a result, fake reviews (opinion spam) are becoming more prevalent and…
This article shows how the text characters that have multiple representations under the Unicode standard are treated by popular operating systems. Whilst most characters have a unique representation in Unicode, some characters such as the…