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

Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either assume prior…

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

The increasing prevalence of Large Language Models (LLMs) in content creation has made distinguishing human-written textual content from LLM-generated counterparts a critical task for multimedia moderation. Existing detectors often rely on…

Social media platforms like Twitter have increasingly relied on Natural Language Processing NLP techniques to analyze and understand the sentiments expressed in the user generated content. One such state of the art NLP model is…

Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods…

In this paper, we study sentiment analysis task where the outcomes are mainly contributed by a few key elements of the inputs. Motivated by the two-streams hypothesis, we propose a neural architecture, named TraceNet, to address this type…

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

Text style transfer techniques are gaining popularity in natural language processing allowing paraphrasing text in the required form: from toxic to neural, from formal to informal, from old to the modern English language, etc. Solving the…

Task-specific word identification aims to choose the task-related words that best describe a short text. Existing approaches require well-defined seed words or lexical dictionaries (e.g., WordNet), which are often unavailable for many…

The rapid advancement of large language models (LLMs) has resulted in increasingly sophisticated AI-generated content, posing significant challenges in distinguishing LLM-generated text from human-written language. Existing detection…

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries…

Analyzing the writing styles of authors and articles is a key to supporting various literary analyses such as author attribution and genre detection. Over the years, rich sets of features that include stylometry, bag-of-words, n-grams have…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Indicators of Compromise (IOCs) are artifacts observed on a network or in an operating system that can be utilized to indicate a computer intrusion and detect cyber-attacks in an early stage. Thus, they exert an important role in the field…

We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical guarantees. Our method builds digital ``marks'' using invisible Unicode…

It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons…

Modern encryption algorithms form the foundation of digital security. However, the widespread use of encryption algorithms results in significant challenges for network defenders in identifying which specific algorithms are being employed.…

We introduce CoEdIT, a state-of-the-art text editing system for writing assistance. CoEdIT takes instructions from the user specifying the attributes of the desired text, such as "Make the sentence simpler" or "Write it in a more neutral…

Abusive language detection has become an increasingly important task as a means to tackle this type of harmful content in social media. There has been a substantial body of research developing models for determining if a social media post…