With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while aligning them with human values has emerged as a critical challenge. In this paper, we investigate an important and unexplored question of whether techniques that successfully jailbreak Large Language Models (LLMs) can be equally effective in jailbreaking MLLMs. To explore this issue, we introduce JailBreakV-28K, a pioneering benchmark designed to assess the transferability of LLM jailbreak techniques to MLLMs, thereby evaluating the robustness of MLLMs against diverse jailbreak attacks. Utilizing a dataset of 2, 000 malicious queries that is also proposed in this paper, we generate 20, 000 text-based jailbreak prompts using advanced jailbreak attacks on LLMs, alongside 8, 000 image-based jailbreak inputs from recent MLLMs jailbreak attacks, our comprehensive dataset includes 28, 000 test cases across a spectrum of adversarial scenarios. Our evaluation of 10 open-source MLLMs reveals a notably high Attack Success Rate (ASR) for attacks transferred from LLMs, highlighting a critical vulnerability in MLLMs that stems from their text-processing capabilities. Our findings underscore the urgent need for future research to address alignment vulnerabilities in MLLMs from both textual and visual inputs.
Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into our society. At the same time, there are also concerns on the potential misuse of this powerful technology, prompting defensive measures from service providers. To overcome such protection, jailbreaking prompts have recently emerged as one of the most effective mechanisms to circumvent security restrictions and elicit harmful content originally designed to be prohibited. Due to the rapid development of LLMs and their ease of access via natural languages, the frontline of jailbreak prompts is largely seen in online forums and among hobbyists. To gain a better understanding of the threat landscape of semantically meaningful jailbreak prompts, we systemized existing prompts and measured their jailbreak effectiveness empirically. Further, we conducted a user study involving 92 participants with diverse backgrounds to unveil the process of manually creating jailbreak prompts. We observed that users often succeeded in jailbreak prompts generation regardless of their expertise in LLMs. Building on the insights from the user study, we also developed a system using AI as the assistant to automate the process of jailbreak prompt generation.
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 new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e.g., "harmful text") has been injected into the images to mislead MLLMs. In this work, we aim to defend against such threats. Specifically, we propose \textbf{Ada}ptive \textbf{Shield} Prompting (\textbf{AdaShield}), which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks without fine-tuning MLLMs or training additional modules (e.g., post-stage content detector). Initially, we present a manually designed static defense prompt, which thoroughly examines the image and instruction content step by step and specifies response methods to malicious queries. Furthermore, we introduce an adaptive auto-refinement framework, consisting of a target MLLM and a LLM-based defense prompt generator (Defender). These components collaboratively and iteratively communicate to generate a defense prompt. Extensive experiments on the popular structure-based jailbreak attacks and benign datasets show that our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks without compromising the model's general capabilities evaluated on standard benign tasks. Our code is available at https://github.com/rain305f/AdaShield.
Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial risks posed by these attacks underscore the need for a thorough understanding of the threats. Yet, research in this area faces challenges due to the lack of a unified goal for such attacks and their reliance on manually crafted prompts, complicating comprehensive assessments of prompt injection robustness. We introduce a unified framework for understanding the objectives of prompt injection attacks and present an automated gradient-based method for generating highly effective and universal prompt injection data, even in the face of defensive measures. With only five training samples (0.3% relative to the test data), our attack can achieve superior performance compared with baselines. Our findings emphasize the importance of gradient-based testing, which can avoid overestimation of robustness, especially for defense mechanisms.
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on. Along with the great potential, there are also increasing concerns over the security of such probabilistic intelligent systems. However, existing studies on LLM security often focus on individual LLM, but without examining the ecosystem through the lens of LLM systems with other objects (e.g., Frontend, Webtool, Sandbox, and so on). In this paper, we systematically analyze the security of LLM systems, instead of focusing on the individual LLMs. To do so, we build on top of the information flow and formulate the security of LLM systems as constraints on the alignment of the information flow within LLM and between LLM and other objects. Based on this construction and the unique probabilistic nature of LLM, the attack surface of the LLM system can be decomposed into three key components: (1) multi-layer security analysis, (2) analysis of the existence of constraints, and (3) analysis of the robustness of these constraints. To ground this new attack surface, we propose a multi-layer and multi-step approach and apply it to the state-of-art LLM system, OpenAI GPT4. Our investigation exposes several security issues, not just within the LLM model itself but also in its integration with other components. We found that although the OpenAI GPT4 has designed numerous safety constraints to improve its safety features, these safety constraints are still vulnerable to attackers. To further demonstrate the real-world threats of our discovered vulnerabilities, we construct an end-to-end attack where an adversary can illicitly acquire the user's chat history, all without the need to manipulate the user's input or gain direct access to OpenAI GPT4. Our demo is in the link: https://fzwark.github.io/LLM-System-Attack-Demo/
Despite the general capabilities of Large Language Models (LLMs) like GPT-4 and Llama-2, these models still request fine-tuning or adaptation with customized data when it comes to meeting the specific business demands and intricacies of tailored use cases. However, this process inevitably introduces new safety threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack), where incorporating just a few harmful examples into the fine-tuning dataset can significantly compromise the model safety. Though potential defenses have been proposed by incorporating safety examples into the fine-tuning dataset to reduce the safety issues, such approaches require incorporating a substantial amount of safety examples, making it inefficient. To effectively defend against the FJAttack with limited safety examples, we propose a Backdoor Enhanced Safety Alignment method inspired by an analogy with the concept of backdoor attacks. In particular, we construct prefixed safety examples by integrating a secret prompt, acting as a "backdoor trigger", that is prefixed to safety examples. Our comprehensive experiments demonstrate that through the Backdoor Enhanced Safety Alignment with adding as few as 11 prefixed safety examples, the maliciously fine-tuned LLMs will achieve similar safety performance as the original aligned models. Furthermore, we also explore the effectiveness of our method in a more practical setting where the fine-tuning data consists of both FJAttack examples and the fine-tuning task data. Our method shows great efficacy in defending against FJAttack without harming the performance of fine-tuning tasks.
With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human brain equipped with multiple web tools to actively interact with external deployed websites. As uncountable Web Agents have been released and such LLM systems are experiencing rapid development and drawing closer to widespread deployment in our daily lives, an essential and pressing question arises: "Are these Web Agents secure?". In this paper, we introduce a novel threat, WIPI, that indirectly controls Web Agent to execute malicious instructions embedded in publicly accessible webpages. To launch a successful WIPI works in a black-box environment. This methodology focuses on the form and content of indirect instructions within external webpages, enhancing the efficiency and stealthiness of the attack. To evaluate the effectiveness of the proposed methodology, we conducted extensive experiments using 7 plugin-based ChatGPT Web Agents, 8 Web GPTs, and 3 different open-source Web Agents. The results reveal that our methodology achieves an average attack success rate (ASR) exceeding 90% even in pure black-box scenarios. Moreover, through an ablation study examining various user prefix instructions, we demonstrated that the WIPI exhibits strong robustness, maintaining high performance across diverse prefix instructions.
Sampling from diffusion probabilistic models (DPMs) is often expensive for high-quality image generation and typically requires many steps with a large model. In this paper, we introduce sampling Trajectory Stitching T-Stitch, a simple yet efficient technique to improve the sampling efficiency with little or no generation degradation. Instead of solely using a large DPM for the entire sampling trajectory, T-Stitch first leverages a smaller DPM in the initial steps as a cheap drop-in replacement of the larger DPM and switches to the larger DPM at a later stage. Our key insight is that different diffusion models learn similar encodings under the same training data distribution and smaller models are capable of generating good global structures in the early steps. Extensive experiments demonstrate that T-Stitch is training-free, generally applicable for different architectures, and complements most existing fast sampling techniques with flexible speed and quality trade-offs. On DiT-XL, for example, 40% of the early timesteps can be safely replaced with a 10x faster DiT-S without performance drop on class-conditional ImageNet generation. We further show that our method can also be used as a drop-in technique to not only accelerate the popular pretrained stable diffusion (SD) models but also improve the prompt alignment of stylized SD models from the public model zoo. Code is released at https://github.com/NVlabs/T-Stitch