Related papers: Detecting High-Stakes Interactions with Activation…

Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit…

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipulation attacks,…

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…

While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Critical networked services enable significant revenue for network operators and, in turn, are regulated by Service Level Agreements (SLAs). In order to ensure SLAs are being met, service levels need to be monitored. One technique for this…

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

With the large-scale adoption of Large Language Models (LLMs) in various applications, there is a growing reliability concern due to their tendency to generate inaccurate text, i.e. hallucinations. In this work, we propose Cross-Layer…

Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human…

Pedestrian safety is a critical component of urban mobility and is strongly influenced by the interactions between pedestrian decision-making and driver yielding behavior at crosswalks. Modeling driver--pedestrian interactions at…

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

Over the past decade, wearable computing devices (``smart glasses'') have undergone remarkable advancements in sensor technology, design, and processing power, ushering in a new era of opportunity for high-density human behavior data.…

Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. However, existing activation safety approaches, trained on…

In high-stake environments like emergency response or elder care, the integration of large language model (LLM), revolutionize risk assessment, resource allocation, and emergency responses in Human Activity Recognition (HAR) systems by…

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post…

The rapid evolution of cyber threats necessitates innovative solutions for detecting and analyzing malicious activity. Honeypots, which are decoy systems designed to lure and interact with attackers, have emerged as a critical component in…