相关论文: MART: Improving LLM Safety with Multi-round Automa…

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…

Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona-Conditioned Adversarial Prompting (PCAP), which conditions…

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Large language models (LLMs) can perform recommendation tasks by taking prompts written in natural language as input. Compared to traditional methods such as collaborative filtering, LLM-based recommendation offers advantages in handling…

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete. In this work, we show that while this self-directed loop…

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed…

The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes…

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

Recent breakthroughs in natural language processing (NLP) have permitted the synthesis and comprehension of coherent text in an open-ended way, therefore translating the theoretical algorithms into practical applications. The large language…

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

We consider the problem of red teaming LLMs on elementary calculations and algebraic tasks to evaluate how various prompting techniques affect the quality of outputs. We present a framework to procedurally generate numerical questions and…

Human motion generation driven by deep generative models has enabled compelling applications, but the ability of text-to-motion (T2M) models to produce realistic motions from text prompts raises security concerns if exploited maliciously.…