Related papers: Context-Sensitive Malicious Spelling Error Correct…
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…
Automatic sarcasm detection is a growing field in computer science. Short text messages are increasingly used for communication, especially over social media platforms such as Twitter. Due to insufficient or missing context, unidentified…
Spam is commonly known as unsolicited or unwanted email messages in the Internet causing potential threat to Internet Security. Users spend a valuable amount of time deleting spam emails. More importantly, ever increasing spam emails occupy…
In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks. Intent Classification on a small dataset is a…
In this paper, we introduce an enhanced textual adversarial attack method, known as Saliency Attention and Semantic Similarity driven adversarial Perturbation (SASSP). The proposed scheme is designed to improve the effectiveness of…
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…
While memes are often humorous, they are frequently used to disseminate hate, causing serious harm to individuals and society. Current approaches to hateful meme detection mainly rely on pre-trained language models. However, less focus has…
Automatic spelling and grammatical correction systems are one of the most widely used tools within natural language applications. In this thesis, we assume the task of error correction as a type of monolingual machine translation where the…
The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information,…
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fraud and abuse detection, remains an area that requires…
State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…
Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative…
In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…
Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters. Few try to attack classifiers by rewriting a whole sentence, due to the…
Learning high-quality embeddings for rare words is a hard problem because of sparse context information. Mimicking (Pinter et al., 2017) has been proposed as a solution: given embeddings learned by a standard algorithm, a model is first…
Attackers create adversarial text to deceive both human perception and the current AI systems to perform malicious purposes such as spam product reviews and fake political posts. We investigate the difference between the adversarial and the…
Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…
It's challenging to customize transducer-based automatic speech recognition (ASR) system with context information which is dynamic and unavailable during model training. In this work, we introduce a light-weight contextual spelling…
Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these…
Judging an action's safety requires knowledge of the context in which the action takes place. To human agents who act in various contexts, this may seem obvious: performing an action such as email deletion may or may not be appropriate…