Related papers: Build it Break it Fix it for Dialogue Safety: Robu…

With the increasing use of machine-learning driven algorithmic judgements, it is critical to develop models that are robust to evolving or manipulated inputs. We propose an extensive analysis of model robustness against linguistic variation…

The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language…

Building user trust in dialogue agents requires smooth and consistent dialogue exchanges. However, agents can easily lose conversational context and generate irrelevant utterances. These situations are called dialogue breakdown, where agent…

The proliferation of social media platforms has led to an increase in the spread of hate speech, particularly targeting vulnerable communities. Unfortunately, existing methods for automatically identifying and blocking toxic language rely…

We present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and…

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT…

Recent advancements in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. While various defence mechanisms have been proposed, there is a lack of comprehensive benchmarks that…

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…

With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is…

Adversarial robustness evaluates the worst-case performance scenario of a machine learning model to ensure its safety and reliability. This study is the first to investigate the robustness of visually grounded dialog models towards textual…

Detection of offensive language in social media is one of the key challenges for social media. Researchers have proposed many advanced methods to accomplish this task. In this report, we try to use the learnings from their approach and…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Humans often employ figurative language use in communication, including during interactions with dialog systems. Thus, it is important for real-world dialog systems to be able to handle popular figurative language constructs like metaphor…

Offensive language detection is an important task for filtering out abusive expressions and improving online user experiences. However, malicious users often attempt to avoid filtering systems through the involvement of textual noises. In…

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

Recent advances in natural language processing (NLP) have led to the development of large language models (LLMs) such as ChatGPT. This paper proposes a methodology for developing and evaluating ChatGPT detectors for French text, with a…

As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatbots are time and cost-intensive, put high cognitive demands…

Chatbots have the risk of generating offensive utterances, which must be avoided. Post-deployment, one way for a chatbot to continuously improve is to source utterance/label pairs from feedback by live users. However, among users are…