Related papers: FreakOut-LLM: The Effect of Emotional Stimuli on S…
Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns that models could…
Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…
Large language models (LLMs) are transforming research on machine learning while galvanizing public debates. Understanding not only when these models work well and succeed but also why they fail and misbehave is of great societal relevance.…
Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task completion. Deployed systems often condition on user profiles or persistent memory, yet agent…
Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…
Large Language Models (LLMs) are integral to modern AI applications, but their safety alignment mechanisms can be bypassed through adversarial prompt engineering. This study investigates emoji-based jailbreaking, where emoji sequences are…
Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…
Large Language Models (LLMs) are increasingly deployed in interactions where they are prompted to adopt personas. This paper investigates whether such persona conditioning affects model safety under bullying, an adversarial manipulation…
Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear. Here, we examine how first-person emotional framing in user-side queries affect LLM performance across six…
Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…
Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context…
Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…
Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…
Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…
Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…
Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…
Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…
Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this assumption with a direction-flipped influence audit: for each scenario, we compare a baseline…
Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark…