相关论文: Fight Back Against Jailbreaking via Prompt Adversa…

This paper proposes a game theoretic framework that models the interaction between prompt engineers and large language models (LLMs) as a two player extensive form game coupled with a Rapidly exploring Random Trees (RRT) search over prompt…

Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities, especially in model API. To fill the research gap, we carry out the…

Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community.…

Large Language Models (LLMs), like ChatGPT, have demonstrated vast potential but also introduce challenges related to content constraints and potential misuse. Our study investigates three key research questions: (1) the number of different…

Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications. However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist. Drawing inspiration from adversarial…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of…

Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by…

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks that induce them to generate harmful content. More recent LLMs…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Large Language Models (LLMs) are attracting significant research attention due to their instruction-following abilities, allowing users and developers to leverage LLMs for a variety of tasks. However, LLMs are vulnerable to prompt-injection…

Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation…

LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses.…

Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment. Existing defense strategies typically rely on predefined static criteria to differentiate between harmful and benign prompts.…

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…

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating,…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…