相关论文: AdvPrompter: Fast Adaptive Adversarial Prompting f…

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Large Language Models (LLMs) have achieved impressive performance in text summarization and are increasingly deployed in real-world applications. However, these systems often inherit associative and framing biases from pre-training data,…

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight is that pretrained, non-autoregressive generative LLMs,…

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…

Large Language Models (LLMs) exhibit remarkable capabilities but are susceptible to adversarial prompts that exploit vulnerabilities to produce unsafe or biased outputs. Existing red-teaming methods often face scalability challenges,…

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptRobust, a robustness…

Large Language Models (LLMs) are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial…

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point…

With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such services can reduce user effort, they also introduce a risk: the…

We propose a new method, Adversarial In-Context Learning (adv-ICL), to optimize prompt for in-context learning (ICL) by employing one LLM as a generator, another as a discriminator, and a third as a prompt modifier. As in traditional…