相关论文: Super Suffixes: Bypassing Text Generation Alignmen…

Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper, we reveal a critical safety inconsistency: LLMs can more…

Diffusion Large Language Models (dLLMs) have recently emerged as a competitive non-autoregressive paradigm due to their unique training and inference approach. However, there is currently a lack of safety study on this novel architecture.…

Although large language models (LLMs) are typically aligned, they remain vulnerable to jailbreaking through either carefully crafted prompts in natural language or, interestingly, gibberish adversarial suffixes. However, gibberish tokens…

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

User authorization-based access privileges are a key feature in many safety-critical systems, but have not been extensively studied in the large language model (LLM) realm. In this work, drawing inspiration from such access control systems,…

Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…

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…

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…

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…

Inspired by the success of large language models (LLMs), there is a significant research shift from traditional graph learning methods to LLM-based graph frameworks, formally known as GraphLLMs. GraphLLMs leverage the reasoning power of…

Currently, large models are prone to generating harmful content when faced with complex attack instructions, significantly reducing their defensive capabilities. To address this issue, this paper proposes a method based on constructing data…

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmful behaviors.…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by…

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Generative AI technologies, particularly Large Language Models (LLMs), are rapidly being adopted across industry, academia, and government sectors, owing to their remarkable capabilities in natural language processing. However, despite…