Related papers: Clean Up the Mess: Addressing Data Pollution in Cr…

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

This paper conducts a comprehensive examination of the infrastructure supporting cryptojacking operations. The analysis elucidates the methodologies, frameworks, and technologies malicious entities employ to misuse computational resources…

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination…

The ransomware threat has loomed over our digital life since 1989. Criminals use this type of cyber attack to lock or encrypt victims' data, often coercing them to pay exorbitant amounts in ransom. The damage ransomware causes ranges from…

In shaping the Internet of Money, the application of blockchain and distributed ledger technologies (DLTs) to the financial sector triggered regulatory concerns. Notably, while the user anonymity enabled in this field may safeguard privacy…

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns…

Semi-supervised machine learning (SSL) is gaining popularity as it reduces the cost of training ML models. It does so by using very small amounts of (expensive, well-inspected) labeled data and large amounts of (cheap, non-inspected)…

Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward…

Cybercrimes are becoming a bigger menace to both people and corporations. It poses a serious challenge to the modern digital world. According to a press release from 2019 Cisco and Cybersecurity Ventures, Cisco stopped seven trillion…

A large number of URLs are made public by various platforms for security analysis, archiving, and paste sharing -- such as VirusTotal, URLScan.io, Hybrid Analysis, the Wayback Machine, and RedHunt. These services may unintentionally expose…

Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter…

Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for…

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Despite the fact that cryptocurrencies themselves have experienced an astonishing rate of adoption over the last decade, cryptocurrency fraud detection is a heavily under-researched problem area. Of all fraudulent activity regarding…

Content safety teams need metrics that reflect what users actually experience, not only what is reported. We study prevalence: the fraction of user views (impressions) that went to content violating a given policy on a given day. Accurate…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Large language models (LLMs) have demonstrated great performance across various benchmarks, showing potential as general-purpose task solvers. However, as LLMs are typically trained on vast amounts of data, a significant concern in their…

A key challenge of big data analytics is how to collect a large volume of (labeled) data. Crowdsourcing aims to address this challenge via aggregating and estimating high-quality data (e.g., sentiment label for text) from pervasive…

Romance-baiting scams have become a major source of financial and emotional harm worldwide. These operations are run by organized crime syndicates that traffic thousands of people into forced labor, requiring them to build emotional…

The advancement of AI technologies, particularly Large Language Models (LLMs), has transformed computing while introducing new security and privacy risks. Prior research shows that cybercriminals are increasingly leveraging uncensored LLMs…