相关论文: Exploring and Mitigating Adversarial Manipulation …

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

AI Large Language Models (LLMs) like ChatGPT are set to reshape some aspects of policymaking processes. Policy practitioners are already using ChatGPT for help with a variety of tasks: from drafting statements, submissions, and…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what may and must not be shared, and the agent must robustly follow that intent even when…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

Voting advice applications (VAAs), which have become increasingly prominent in European elections, are seen as a successful tool for boosting electorates' political knowledge and engagement. However, VAAs' complex language and rigid…

Each day, individuals set behavioral goals such as eating healthier, exercising regularly, or increasing productivity. While psychological frameworks (i.e., goal setting and implementation intentions) can be helpful, they often need…

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in…

The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting…

Student commitment towards a learning recommendation is not separable from their understanding of the reasons it was recommended to them; and their ability to modify it based on that understanding. Among explainability approaches, chatbots…

Can we trust Large Language Models (LLMs) to accurately predict scam? This paper investigates the vulnerabilities of LLMs when facing adversarial scam messages for the task of scam detection. We addressed this issue by creating a…

Personal attacks have become a notable feature of U.S. presidential debates and play an important role in shaping public perception during elections. Detecting such attacks can improve transparency in political discourse and provide…

Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

The emergence of LLM (Large Language Model) integrated virtual assistants has brought about a rapid transformation in communication dynamics. During virtual assistant development, some developers prefer to leverage the system message, also…

Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of complete solutions…

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can…

Accurate detection of errors in large language models (LLM) responses is central to the success of scalable oversight, or providing effective supervision to superhuman intelligence. Yet, self-diagnosis is often unreliable on complex tasks…