相关论文: Gradient-Based Language Model Red Teaming

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt. By minimizing data exposure to LLM, the framework addresses the security and legal…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Prompt-based learning has been proved to be an effective way in pre-trained language models (PLMs), especially in low-resource scenarios like few-shot settings. However, the trustworthiness of PLMs is of paramount significance and potential…

While tool learning significantly enhances the capabilities of large language models (LLMs), it also introduces substantial security risks. Prior research has revealed various vulnerabilities in traditional LLMs during tool learning.…

Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In this paper, we present a systematic appraisal of GCG and its…

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and…

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to…

Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents, and AI assistants. However, security…

In recent years, Large Language Models (LLMs) have demonstrated remarkable proficiency in comprehending and generating natural language, with a growing prevalence in the domain of recommendation systems. However, LLMs still face a…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

Language Identification (LI) is crucial for various natural language processing tasks, serving as a foundational step in applications such as sentiment analysis, machine translation, and information retrieval. In multilingual societies like…

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety…

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Machine learning models are vulnerable to adversarial attacks that can often cause misclassification by introducing small but well designed perturbations. In this paper, we explore, in the setting of classical composite hypothesis testing,…

This case study investigates the task of job classification in a real-world setting, where the goal is to determine whether an English-language job posting is appropriate for a graduate or entry-level position. We explore multiple…

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.…

As large language models (LLMs) have advanced rapidly, concerns regarding their safety have become prominent. In this paper, we discover that code-switching in red-teaming queries can effectively elicit undesirable behaviors of LLMs, which…

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…