Related papers: Mitigating Covertly Unsafe Text within Natural Lan…
Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which…
Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for…
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…
Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…
Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate…
The use of short text messages in social media and instant messaging has become a popular communication channel during the last years. This rising popularity has caused an increment in messaging threats such as spam, phishing or malware as…
Warning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating…
The exchange of personal information in digital environments poses significant risks, including identity theft, privacy breaches, and data misuse. Addressing these challenges requires a deep understanding of user behavior and mental models…
Natural Language Generation tools, such as chatbots that can generate human-like conversational text, are becoming more common both for personal and professional use. However, there are concerns about their trustworthiness and ethical…
Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing…
This paper analyzes the safety of Large Language Models (LLMs) in interactions with children below age of 18 years. Despite the transformative applications of LLMs in various aspects of children's lives such as education and therapy, there…
Scientific information expresses human understanding of nature. This knowledge is largely disseminated in different forms of text, including scientific papers, news articles, and discourse among people on social media. While important for…
Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate…
Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is…
With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content generation, human-computer interaction, machine translation, and…
Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concepts like "hate…
Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…
When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…
Text-to-image (T2I) models have emerged as a significant advancement in generative AI; however, there exist safety concerns regarding their potential to produce harmful image outputs even when users input seemingly safe prompts. This…
The Go programming language aims to provide memory and thread safety through measures such as automated memory management with garbage collection and a strict type system. However, it also offers a way of circumventing this safety net…