Related papers: Tuning for TraceTarnish: Techniques, Trends, and T…

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating…

Recent studies show that text-to-image (T2I) models are vulnerable to adversarial attacks, especially with noun perturbations in text prompts. In this study, we investigate the impact of adversarial attacks on different POS tags within text…

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, failing to disrupt proprietary LLMs consistently. To reliably…

An individual's variation in writing style is often a function of both social and personal attributes. While structured social variation has been extensively studied, e.g., gender based variation, far less is known about how to characterize…

To identify and classify toxic online commentary, the modern tools of data science transform raw text into key features from which either thresholding or learning algorithms can make predictions for monitoring offensive conversations. We…

While text-conditional 3D object generation and manipulation have seen rapid progress, the evaluation of coherence between generated 3D shapes and input textual descriptions lacks a clear benchmark. The reason is twofold: a) the low quality…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Watermarking is a key technique for detecting AI-generated text. In this work, we study its vulnerabilities and introduce the Smoothing Attack, a novel watermark removal method. By leveraging the relationship between the model's confidence…

Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the "locality hypothesis", suppressing isolated neurons or features. However, harmful…

AI-driven penetration testing agents are now capable of autonomously executing attacks within compromised networks. Identifying the model family that controls the active sessions of such agents provides valuable information towards…

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

In the age of advanced large language models (LLMs), the boundaries between human and AI-generated text are becoming increasingly blurred. We address the challenge of segmenting mixed-authorship text, that is identifying transition points…

Accurate and reliable personality assessment plays a vital role in many fields, such as emotional intelligence, mental health diagnostics, and personalized education. Unlike fleeting emotions, personality traits are stable, often…

When reading news articles on social networking services and news sites, readers can view comments marked by other people on these articles. By reading these comments, a reader can understand the public opinion about the news, and it is…

The fundamental building block of social influence is for one person to elicit a response in another. Researchers measuring a "response" in social media typically depend either on detailed models of human behavior or on platform-specific…

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's…

The rapid proliferation of harmful and emotionally damaging content on social media platforms has intensified concerns regarding societal harm. While content moderation efforts primarily focus on detecting and removing harmful posts, less…

Existing text scoring methods require a large corpus, struggle with short texts, or require hand-labeled data. We develop a text scoring framework that leverages generative large language models (LLMs) to (1) set texts against the backdrop…

Authorship attribution aims to identify the author of a text based on the stylometric analysis. Authorship obfuscation, on the other hand, aims to protect against authorship attribution by modifying a text's style. In this paper, we…