相关论文: Red Teaming Language Models with Language Models

User interactions with conversational agents (CAs) evolve in the era of heavily guardrailed large language models (LLMs). As users push beyond programmed boundaries to explore and build relationships with these systems, there is a growing…

Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance…

Rapid advancements in large language models (LLMs) have revitalized in LLM-based agents, exhibiting impressive human-like behaviors and cooperative capabilities in various scenarios. However, these agents also bring some exclusive risks,…

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

Eliciting harmful behavior from large language models (LLMs) is an important task to ensure the proper alignment and safety of the models. Often when training LLMs, ethical guidelines are followed yet alignment failures may still be…

In the evolving landscape of online communication, hate speech detection remains a formidable challenge, further compounded by the diversity of digital platforms. This study investigates the effectiveness and adaptability of pre-trained and…

Generative AI, including large language models (LLMs) have the potential -- and already are being used -- to increase the speed, scale, and types of unsafe conversations online. LLMs lower the barrier for entry for bad actors to create…

As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted…

Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP. The emerging large language models (LLMs), such as ChatGPT, can potentially further accentuate this…

Pretrained Language Models (PLMs) harbor inherent social biases that can result in harmful real-world implications. Such social biases are measured through the probability values that PLMs output for different social groups and attributes…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal, we focus on locally…

Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LLM generations on new…

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…

The proliferation of Large Language Models (LLMs), such as ChatGPT, has raised concerns about their potential impact on academic integrity, prompting the need for LLM-resistant exam designs. This article investigates the performance of LLMs…

Large language models (LLMs) are becoming increasingly important for machine learning applications. However, it can be challenging to align LLMs with our intent, particularly when we want to generate content that is preferable over others…

Despite the continued research and progress in building secure systems, Android applications continue to be ridden with vulnerabilities, necessitating effective detection methods. Current strategies involving static and dynamic analysis…

This paper introduces ChatbotManip, a novel dataset for studying manipulation in Chatbots. It contains simulated generated conversations between a chatbot and a (simulated) user, where the chatbot is explicitly asked to showcase…