相关论文: Antelope: Potent and Concealed Jailbreak Attack St…

Recent research finds CNN models for image classification demonstrate overlapped adversarial vulnerabilities: adversarial attacks can mislead CNN models with small perturbations, which can effectively transfer between different models…

Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, failing to disrupt proprietary LLMs consistently. To reliably…

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Diffusion-based image generation models have advanced rapidly but pose a safety risk due to their potential to generate Not-Safe-For-Work (NSFW) content. Existing NSFW detection methods mainly operate either before or after image…

Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vulnerable because they process both text and images, creating broader attack surfaces.…

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…

The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. Though prior work has explored backdoor attacks against diffusion models for image or unconditional graph generation,…

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual jailbreaking attacks can manipulate open-source MLLMs more…

Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. Among existing approaches, reconstruction-based methods have emerged as a prominent…

Adversarial examples pose significant threats to deep neural networks (DNNs), and their property of transferability in the black-box setting has led to the emergence of transfer-based attacks, making it feasible to target real-world…

Given the need to evaluate the robustness of face recognition (FR) models, many efforts have focused on adversarial patch attacks that mislead FR models by introducing localized perturbations. Impersonation attacks are a significant threat…

Diffusion models (DMs) are regarded as one of the most advanced generative models today, yet recent studies suggest that they are vulnerable to backdoor attacks, which establish hidden associations between particular input patterns and…

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…

The recent advances in diffusion models (DMs) have revolutionized the generation of realistic and complex images. However, these models also introduce potential safety hazards, such as producing harmful content and infringing data…

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…